Upload README.md
Browse files
README.md
CHANGED
|
@@ -92,14 +92,14 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
|
|
| 92 |
|
| 93 |
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
|
| 94 |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
|
| 95 |
-
| [main](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/main) | 4 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) |
|
| 96 |
-
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) |
|
| 97 |
-
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) |
|
| 98 |
-
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) |
|
| 99 |
-
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) |
|
| 100 |
-
| [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) |
|
| 101 |
-
| [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) |
|
| 102 |
-
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) |
|
| 103 |
|
| 104 |
<!-- README_GPTQ.md-provided-files end -->
|
| 105 |
|
|
|
|
| 92 |
|
| 93 |
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
|
| 94 |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
|
| 95 |
+
| [main](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/main) | 4 | 128 | No | 0.01 | [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. |
|
| 96 |
+
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.01 | [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. |
|
| 97 |
+
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.01 | [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. |
|
| 98 |
+
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.01 | [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. |
|
| 99 |
+
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.01 | [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. |
|
| 100 |
+
| [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.95 GB | No | 8-bit, with group size 64g and Act Order for even higher inference quality. Poor AutoGPTQ CUDA speed. |
|
| 101 |
+
| [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.01 | [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 without Act Order to improve AutoGPTQ speed. |
|
| 102 |
+
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.01 | [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. |
|
| 103 |
|
| 104 |
<!-- README_GPTQ.md-provided-files end -->
|
| 105 |
|