from transformers import AutoTokenizer, TextGenerationPipeline from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig import logging

logging.basicConfig( format="%(asctime)s %(levelname)s [%(name)s] %(message)s", level=logging.INFO, datefmt="%Y-%m-%d %H:%M:%S" )

pretrained_model_dir = "Qwen/Qwen1.5-7B-Chat" quantized_model_dir = "/gptq_model-4bit-128g"

tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir, use_fast=True) examples = [ tokenizer( "auto-gptq is an easy-to-use model quantization library with user-friendly apis, based on GPTQ algorithm." ) ]

quantize_config = BaseQuantizeConfig( bits=4, # quantize model to 4-bit group_size=128, # it is recommended to set the value to 128 desc_act=False, # set to False can significantly speed up inference but the perplexity may slightly bad )

load un-quantized model, by default, the model will always be loaded into CPU memory

model = AutoGPTQForCausalLM.from_pretrained(pretrained_model_dir, quantize_config)

quantize model, the examples should be list of dict whose keys can only be "input_ids" and "attention_mask"

model.quantize(examples)

save quantized model

model.save_quantized(quantized_model_dir)

save quantized model using safetensors

model.save_quantized(quantized_model_dir, use_safetensors=True)

push quantized model to Hugging Face Hub.

to use use_auth_token=True, Login first via huggingface-cli login.

or pass explcit token with: use_auth_token="hf_xxxxxxx"

(uncomment the following three lines to enable this feature)

repo_id = f"YourUserName/{quantized_model_dir}"

commit_message = f"AutoGPTQ model for {pretrained_model_dir}: {quantize_config.bits}bits, gr{quantize_config.group_size}, desc_act={quantize_config.desc_act}"

model.push_to_hub(repo_id, commit_message=commit_message, use_auth_token=True)

alternatively you can save and push at the same time

(uncomment the following three lines to enable this feature)

repo_id = f"YourUserName/{quantized_model_dir}"

commit_message = f"AutoGPTQ model for {pretrained_model_dir}: {quantize_config.bits}bits, gr{quantize_config.group_size}, desc_act={quantize_config.desc_act}"

model.push_to_hub(repo_id, save_dir=quantized_model_dir, use_safetensors=True, commit_message=commit_message, use_auth_token=True)

load quantized model to the first GPU

model = AutoGPTQForCausalLM.from_quantized(quantized_model_dir, device="cuda:0")

download quantized model from Hugging Face Hub and load to the first GPU

model = AutoGPTQForCausalLM.from_quantized(repo_id, device="cuda:0", use_safetensors=True, use_triton=False)

inference with model.generate

print(tokenizer.decode(model.generate(**tokenizer("auto_gptq is", return_tensors="pt").to(model.device))[0]))

or you can also use pipeline

pipeline = TextGenerationPipeline(model=model, tokenizer=tokenizer) print(pipeline("auto-gptq is")[0]["generated_text"])