TheBloke commited on
Commit
4ba8b8d
1 Parent(s): 4406157

Initial GPTQ model commit

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -70,12 +70,12 @@ All GPTQ files are made with AutoGPTQ.
70
 
71
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
72
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
73
- | [main](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GPTQ/tree/main) | 4 | 128 | No | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 7.26 GB | Yes | AutoGPTQ | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
74
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 8.00 GB | Yes | AutoGPTQ | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
75
- | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 7.51 GB | Yes | AutoGPTQ | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
76
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 7.26 GB | Yes | AutoGPTQ | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
77
- | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 13.36 GB | No | AutoGPTQ | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
78
- | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 13.65 GB | No | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
79
 
80
  ## How to download from branches
81
 
 
70
 
71
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
72
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
73
+ | [main](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
74
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
75
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.51 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
76
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
77
+ | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
78
+ | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/vicuna-13B-v1.5-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
79
 
80
  ## How to download from branches
81