mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Add support for the latest GPTQ models with group-size (#530)

Browse source 
**Warning: old 4-bit weights will not work anymore!**

See here how to get up to date weights: https://github.com/oobabooga/text-generation-webui/wiki/LLaMA-model#step-2-get-the-pre-converted-weights
This commit is contained in:
oobabooga 2023-03-26 00:11:33 -03:00 • committed by GitHub
parent 8c8e8b4450
commit 49c10c5570
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 64 additions and 43 deletions
Download patch file Download diff file Expand all files Collapse all files

8
README.md
View file

@ -176,10 +176,10 @@ Optionally, you can use the following command-line flags:
| `--cai-chat` | Launch the web UI in chat mode with a style similar to Character.AI's. If the file `img_bot.png` or `img_bot.jpg` exists in the same folder as server.py, this image will be used as the bot's profile picture. Similarly, `img_me.png` or `img_me.jpg` will be used as your profile picture. |
| `--cpu` | Use the CPU to generate text.|
| `--load-in-8bit` | Load the model with 8-bit precision.|
| `--load-in-4bit` | DEPRECATED: use `--gptq-bits 4` instead. |
| `--gptq-bits GPTQ_BITS` | GPTQ: Load a pre-quantized model with specified precision. 2, 3, 4 and 8 (bit) are supported. Currently only works with LLaMA and OPT. |
| `--gptq-model-type MODEL_TYPE` | GPTQ: Model type of pre-quantized model. Currently only LLaMa and OPT are supported. |
| `--gptq-pre-layer GPTQ_PRE_LAYER` | GPTQ: The number of layers to preload. |
| `--wbits WBITS` | GPTQ: Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported. |
| `--model_type MODEL_TYPE` | GPTQ: Model type of pre-quantized model. Currently only LLaMA and OPT are supported. |
| `--groupsize GROUPSIZE` | GPTQ: Group size. |
| `--pre_layer PRE_LAYER` | GPTQ: The number of layers to preload. |
| `--bf16` | Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU. |
| `--auto-devices` | Automatically split the model across the available GPU(s) and CPU.|
| `--disk` | If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk. |