Upload README.md

README.md

@@ -96,7 +96,9 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
 | [main](https://huggingface.co/TheBloke/Spicyboros-c34b-2.2-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 17.69 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. | 
 | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Spicyboros-c34b-2.2-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 18.33 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. | 
 | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Spicyboros-c34b-2.2-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 20.28 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. | 
-| [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/Spicyboros-c34b-2.2-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 14.14 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
+| [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/Spicyboros-c34b-2.2-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 14.14 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. | 
+| [gptq-3bit-32g-actorder_True](https://huggingface.co/TheBloke/Spicyboros-c34b-2.2-GPTQ/tree/gptq-3bit-32g-actorder_True) | 3 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 15.99 GB | No | 3-bit, with group size 64g and act-order. Highest quality 3-bit option. | 
+| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Spicyboros-c34b-2.2-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 34.30 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
 
 <!-- README_GPTQ.md-provided-files end -->
 
@@ -355,9 +357,9 @@ __*I strongly suggest adding stopping criteria/early inference stopping on "USER
 
 ### Fine-tuning details
 
-https://gist.github.com/jondurbin/e94d5a0eb3868db2877413f53d59fb37
+https://gist.github.com/jondurbin/51a336c582a224de197ba1d2c6b1da97
 
-*Note: I used checkpoint 350 for final model, not the full 5 epochs!*
+*Note: I used checkpoint 750 for final model!*
 
 ### Helpful usage tips