simcop2387/AutoGPTQ
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 1 Wiki Activity

update tutorial

Browse source
This commit is contained in:
PanQiWei 2023-05-24 18:31:59 +08:00
parent 065fd1de35
commit ac14180946
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
docs/tutorial/01-Quick-Start.md
View file

@ -78,9 +78,9 @@ Pretrained model's config and the quantize config will also be saved with file n
Instead of `.from_pretrained`, you should use `.from_quantized` to load a quantized model. Instead of `.from_pretrained`, you should use `.from_quantized` to load a quantized model.
```python ```python
device = "cuda:0" device = "cuda:0"
model = AutoGPTQForCausalLM.from_quantized(quantized_model_dir, use_triton=False) model = AutoGPTQForCausalLM.from_quantized(quantized_model_dir, device=device)
``` ```
This will first read and load `quantize_config.json` in `opt-125m-4bit-128g` directory, then based on the values of `bits` and `group_size` in it, load `gptq_model-4bit-128g.bin` model file into the first GPU. This will first read and load `quantize_config.json` in `opt-125m-4bit-128g` directory, then based on the values of `bits` and `group_size` in it, load `gptq_model-4bit-128g.bin` model file into the first visible GPU.
Then you can initialize 🤗 Transformers' `TextGenerationPipeline` and do inference. Then you can initialize 🤗 Transformers' `TextGenerationPipeline` and do inference.
```python ```python