Zamba2-1.2B-instruct

Name: Zamba2-1.2B-instruct
Author: Zyphra

53.5K

GPT-3 class

1.2B

license:apache-2.0

Zyphra

Language Model

OTHER

1.2B params

Fair

54K downloads

Community-tested

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

3GB+ RAM

Mobile

Laptop

Server

Quick Summary

Zamba2-1.2B-instruct is obtained from Zamba2-1.2B by fine-tuning on instruction-following and chat datasets. Specifically: 1. SFT of the base Zamba2-1.2B model...

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

2GB+ RAM

Code Examples

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

Inferencepythontransformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Instantiate model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-1.2B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-1.2B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

# Format the input as a chat template
prompt = "What factors contributed to the fall of the Roman Empire?"
sample = [{'role': 'user', 'content': prompt}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

# Tokenize input and generate output
input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))

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.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.