xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-11 11:35:44 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Doc] fix the autoAWQ example (#7937)

Browse Source
This commit is contained in:
Stas Bekman 2024-08-28 05:12:32 -07:00 committed by GitHub
parent f52a43a8b9
commit 98c12cffe5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
docs/source/quantization/auto_awq.rst
View File

@ -19,27 +19,31 @@ You can quantize your own models by installing AutoAWQ or picking one of the `40
$ pip install autoawq $ pip install autoawq
After installing AutoAWQ, you are ready to quantize a model. Here is an example of how to quantize Vicuna 7B v1.5: After installing AutoAWQ, you are ready to quantize a model. Here is an example of how to quantize `mistralai/Mistral-7B-Instruct-v0.2`:
.. code-block:: python .. code-block:: python
from awq import AutoAWQForCausalLM from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer from transformers import AutoTokenizer
model_path = 'lmsys/vicuna-7b-v1.5' model_path = 'mistralai/Mistral-7B-Instruct-v0.2'
quant_path = 'vicuna-7b-v1.5-awq' quant_path = 'mistral-instruct-v0.2-awq'
quant_config = { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" } quant_config = { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" }
# Load model # Load model
model = AutoAWQForCausalLM.from_pretrained(model_path, **{"low_cpu_mem_usage": True}) model = AutoAWQForCausalLM.from_pretrained(
model_path, **{"low_cpu_mem_usage": True, "use_cache": False}
)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
# Quantize # Quantize
model.quantize(tokenizer, quant_config=quant_config) model.quantize(tokenizer, quant_config=quant_config)
# Save quantized model # Save quantized model
model.save_quantized(quant_path) model.save_quantized(quant_path)
tokenizer.save_pretrained(quant_path) tokenizer.save_pretrained(quant_path)
print(f'Model is quantized and saved at "{quant_path}"')
To run an AWQ model with vLLM, you can use `TheBloke/Llama-2-7b-Chat-AWQ <https://huggingface.co/TheBloke/Llama-2-7b-Chat-AWQ>`_ with the following command: To run an AWQ model with vLLM, you can use `TheBloke/Llama-2-7b-Chat-AWQ <https://huggingface.co/TheBloke/Llama-2-7b-Chat-AWQ>`_ with the following command: