justinthelaw
/

Hermes-2-Pro-Mistral-7B-4bit-32g-GPTQ

Model card Files Files and versions Community

justinthelaw commited on Aug 1

Commit

e1e25d4

•

1 Parent(s): 7ee0383

fix README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ tags:
 base_model: mistralai/Mistral-7B-v0.1
 datasets:
 - teknium/OpenHermes-2.5
-- VMWare/open-instruct
 ---
 # Hermes-2-Pro-Mistral-7B GPTQ 4-bit 32g Group Size
@@ -32,7 +32,7 @@ datasets:
 <!-- description start -->
 ## Description
-This repo contains GPTQ 4-bit, 128g Group Size, quantized model files for the recently released upgrade of [Hermes-2-Pro-Mistral-7B](https://huggingface.co/justinthelaw/Hermes-2-Pro-Mistral-7B-4bit-128g-instruct).
 <!-- README_GPTQ.md-provided-files start -->
 ## GPTQ parameters
@@ -41,7 +41,7 @@ Models are released as sharded safetensors files.
 | Bits | GS | GPTQ Dataset | Seq Len | Size |
 | ---- | -- | ----------- | ------- | ---- |
-| 4 | 128 | [VMWare Open Instruct](https://huggingface.co/datasets/vmware/open-instruct) | 128,000  | 2.28 GB
 <!-- README_GPTQ.md-provided-files end -->

 base_model: mistralai/Mistral-7B-v0.1
 datasets:
 - teknium/OpenHermes-2.5
+- vmware/open-instruct
 ---
 # Hermes-2-Pro-Mistral-7B GPTQ 4-bit 32g Group Size
 <!-- description start -->
 ## Description
+This repo contains GPTQ 4-bit, 32g Group Size, quantized model files for the Nous Research [Hermes-2-Pro-Mistral-7B](https://huggingface.co/justinthelaw/Hermes-2-Pro-Mistral-7B-4bit-128g-instruct) fine-tune of the [Mistral-7b-Instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) model.
 <!-- README_GPTQ.md-provided-files start -->
 ## GPTQ parameters
 | Bits | GS | GPTQ Dataset | Seq Len | Size |
 | ---- | -- | ----------- | ------- | ---- |
+| 4 | 32 | [VMWare Open Instruct](https://huggingface.co/datasets/vmware/open-instruct) | 128,000  | 4.57 GB
 <!-- README_GPTQ.md-provided-files end -->