Hugging Face's logo

TheBloke
/
airoboros-33B-GPT4-m2.0-GPTQ

Text Generation
Transformers
Safetensors
llama
text-generation-inference
4-bit precision
gptq
Model card Files Community
TheBloke commited on
Commit
fd4a8f0
·
1 Parent(s): 3dfcd4d

Initial GPTQ model commit

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -58,10 +58,10 @@ Each separate quant is in a different branch. See below for instructions on fet
58
  | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/airoboros-33B-GPT4-m2.0-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 19.44 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. |
59
  | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/airoboros-33B-GPT4-m2.0-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 18.18 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. |
60
  | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/airoboros-33B-GPT4-m2.0-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 17.55 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. |
61
- | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/airoboros-33B-GPT4-m2.0-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | Processing, coming soon | No | AutoGPTQ | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
62
- | [gptq-3bit-128g-actorder_False](https://huggingface.co/TheBloke/airoboros-33B-GPT4-m2.0-GPTQ/tree/gptq-3bit-128g-actorder_False) | 3 | 128 | No | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | Processing, coming soon | No | AutoGPTQ | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. |
63
- | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/airoboros-33B-GPT4-m2.0-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | Processing, coming soon | No | AutoGPTQ | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
64
- | [gptq-3bit-64g-actorder_True](https://huggingface.co/TheBloke/airoboros-33B-GPT4-m2.0-GPTQ/tree/gptq-3bit-64g-actorder_True) | 3 | 64 | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | Processing, coming soon | No | AutoGPTQ | 3-bit, with group size 64g and act-order. Highest quality 3-bit option. Poor AutoGPTQ CUDA speed. |
65
 
66
  ## How to download from branches
67
 
 
58
  | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/airoboros-33B-GPT4-m2.0-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 19.44 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. |
59
  | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/airoboros-33B-GPT4-m2.0-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 18.18 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. |
60
  | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/airoboros-33B-GPT4-m2.0-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 17.55 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. |
61
+ | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/airoboros-33B-GPT4-m2.0-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 12.92 GB | No | AutoGPTQ | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
62
+ | [gptq-3bit-128g-actorder_False](https://huggingface.co/TheBloke/airoboros-33B-GPT4-m2.0-GPTQ/tree/gptq-3bit-128g-actorder_False) | 3 | 128 | No | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 13.51 GB | No | AutoGPTQ | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. |
63
+ | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/airoboros-33B-GPT4-m2.0-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 13.51 GB | No | AutoGPTQ | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
64
+ | [gptq-3bit-64g-actorder_True](https://huggingface.co/TheBloke/airoboros-33B-GPT4-m2.0-GPTQ/tree/gptq-3bit-64g-actorder_True) | 3 | 64 | Yes | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 14.11 GB | No | AutoGPTQ | 3-bit, with group size 64g and act-order. Highest quality 3-bit option. Poor AutoGPTQ CUDA speed. |
65
 
66
  ## How to download from branches
67