DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16
1.5K
1
14.0B
license:mit
by
RedHatAI
Language Model
OTHER
14B params
New
1K downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
32GB+ RAM
Mobile
Laptop
Server
Quick Summary
AI model with specialized capabilities.
Device Compatibility
Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
14GB+ RAM
Code Examples
Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Use with vLLMpythontransformers
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)
messages_list = [
[{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]
prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")Creationpythontransformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
model_name = model_stub.split("/")[-1]
num_samples = 2048
max_seq_len = 8192
tokenizer = AutoTokenizer.from_pretrained(model_stub)
model = AutoModelForCausalLM.from_pretrained(
model_stub,
device_map="auto",
torch_dtype="auto",
)
def preprocess_fn(example):
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
targets="Linear",
scheme="W4A16",
ignore=["lm_head"],
dampening_frac=0.01,
)
# Apply quantization
oneshot(
model=model,
dataset=ds,
recipe=recipe,
max_seq_length=max_seq_len,
num_calibration_samples=num_samples,
)
# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")textvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtextvllm
lm_eval \
--model vllm \
--model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
--tasks openllm \
--write_out \
--batch_size auto \
--output_path output_dir \
--show_configtext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_servertext
guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_serverDeploy This Model
Production-ready deployment in minutes
Together.ai
Instant API access to this model
Production-ready inference API. Start free, scale to millions.
Try Free APIReplicate
One-click model deployment
Run models in the cloud with simple API. No DevOps required.
Deploy NowDisclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.