BPO

93

21

2 languages

llama

by

zai-org

Language Model

OTHER

New

93 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

Unknown

Mobile

Laptop

Server

Quick Summary

Black-Box Prompt Optimization: Aligning Large Language Models without Model Training - Repository: https://github.

Code Examples

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Inference codepythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Your-Model-Path'

prompt_template = "[INST] You are an expert prompt engineer. Please help me improve this prompt to get a more helpful and harmless response:\n{} [/INST]"

model = AutoModelForCausalLM.from_pretrained(model_path).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = 'Tell me about Harry Potter'

prompt = prompt_template.format(text)
model_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
output = model.generate(**model_inputs, max_new_tokens=1024, do_sample=True, top_p=0.9, temperature=0.6, num_beams=1)
resp = tokenizer.decode(output[0], skip_special_tokens=True).split('[/INST]')[1].strip()

print(resp)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.