TheBloke commited on
Commit
ce26aa9
·
1 Parent(s): 2f30b2f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -100,10 +100,10 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
100
 
101
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
102
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
103
- | main | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 94.5 GB | No | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
104
- | gptq-3bit-128g-actorder_True | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 73.81 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
105
- | gptq-3bit--1g-actorder_True | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 70.54 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
106
  | gptq-4bit--1g-actorder_True | 4 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 92.74 GB | No | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
 
 
107
 
108
  <!-- README_GPTQ.md-provided-files end -->
109
 
 
100
 
101
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
102
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
103
+ | main | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 94.5 GB | No | 4-bit, with Act Order and group size 128g. Higher quality than group_size=None, but also higher VRAM usage. |
 
 
104
  | gptq-4bit--1g-actorder_True | 4 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 92.74 GB | No | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
105
+ | gptq-3bit-128g-actorder_True | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 73.81 GB | No | 3-bit, so much lower VRAM requirements but worse quality than 4-bit. With group size 128g and act-order. Higher quality than 3bit-128g-False. |
106
+ | gptq-3bit--1g-actorder_True | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 70.54 GB | No | 3-bit, so much lower VRAM requirements but worse quality than 4-bit. With no group size for lowest possible VRAM requirements. Lower quality than 3-bit 128g. |
107
 
108
  <!-- README_GPTQ.md-provided-files end -->
109