Qwen2.5-1.5B-FP8-dynamic

4
license:apache-2.0
by
RedHatAI
Language Model
OTHER
1.5B params
New
4 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
4GB+ RAM
Mobile
Laptop
Server
Quick Summary

Model Overview - Model Architecture: Qwen2 - Input: Text - Output: Text - Model Optimizations: - Activation quantization: INT8 - Weight quantization: INT8 - Int...

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
2GB+ RAM

Code Examples

Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
Deploymentpythontransformers
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Qwen2.5-1.5B-FP8-dynamic"
number_gpus = 1
max_model_len = 8192

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)

outputs = llm.generate(prompt, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto
textvllm
lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Qwen2.5-1.5B-FP8-dynamic",dtype=auto,gpu_memory_utilization=0.9,add_bos_token=True,max_model_len=4096,enable_chunk_prefill=True,tensor_parallel_size=1 \
  --tasks openllm \
  --batch_size auto

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.