Add ExLlamaV2 quant link (#2)
Browse files- Add ExLlamaV2 quant link (4f6c322aed68d41550aa35d63552785446479b1e)
Co-authored-by: Bartowski <[email protected]>
README.md
CHANGED
|
@@ -86,4 +86,8 @@ Hercules-2.5-Mistral-7B is fine-tuned from the following sources:
|
|
| 86 |
This model was fine-tuned using the TPU-Alignment repository. https://github.com/Locutusque/TPU-Alignment
|
| 87 |
|
| 88 |
# Updates
|
| 89 |
-
- **🔥 Earned a score of nearly 64 on Open LLM Leaderboard, outperforming most merge-free SFT mistral fine-tunes 🔥**
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
This model was fine-tuned using the TPU-Alignment repository. https://github.com/Locutusque/TPU-Alignment
|
| 87 |
|
| 88 |
# Updates
|
| 89 |
+
- **🔥 Earned a score of nearly 64 on Open LLM Leaderboard, outperforming most merge-free SFT mistral fine-tunes 🔥**
|
| 90 |
+
|
| 91 |
+
# Quants
|
| 92 |
+
|
| 93 |
+
exl2 by @bartowski https://huggingface.co/bartowski/Hercules-2.5-Mistral-7B-exl2
|