Upload README.md
Browse files
README.md
CHANGED
|
@@ -101,8 +101,9 @@ Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with T
|
|
| 101 |
| [main](https://huggingface.co/TheBloke/Ziya-Coding-34B-v1.0-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 17.69 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
|
| 102 |
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Ziya-Coding-34B-v1.0-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 18.33 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
|
| 103 |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Ziya-Coding-34B-v1.0-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 20.28 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
|
| 104 |
-
| gptq-3bit-128g-actorder_True | 3 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 |
|
| 105 |
-
| gptq-8bit-128g-actorder_True | 8 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 |
|
|
|
|
| 106 |
|
| 107 |
<!-- README_GPTQ.md-provided-files end -->
|
| 108 |
|
|
|
|
| 101 |
| [main](https://huggingface.co/TheBloke/Ziya-Coding-34B-v1.0-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 17.69 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
|
| 102 |
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Ziya-Coding-34B-v1.0-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 18.33 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
|
| 103 |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Ziya-Coding-34B-v1.0-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 20.28 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
|
| 104 |
+
| [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/Ziya-Coding-34B-v1.0-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 14.14 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
|
| 105 |
+
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Ziya-Coding-34B-v1.0-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 34.30 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
|
| 106 |
+
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Ziya-Coding-34B-v1.0-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | None | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 34.30 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
|
| 107 |
|
| 108 |
<!-- README_GPTQ.md-provided-files end -->
|
| 109 |
|