|
--- |
|
license: apache-2.0 |
|
pipeline_tag: text-generation |
|
--- |
|
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/x44nNbPTpv0zGTqA1Jb2q.png) |
|
|
|
--- |
|
**NOTE** |
|
Model and Model card from: https://huggingface.co/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp |
|
This repo is mainly to share quantized gguf to use with clients like LMStudio, contains q4 and q8 quantization along with f16. |
|
|
|
How to quantize? |
|
https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#prepare-data--run |
|
--- |
|
|
|
# OpenHermes-2.5-neural-chat-v3-3-Slerp |
|
Slerp merge of [OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) and [neural-chat-7b-v3-3](https://huggingface.co/Intel/neural-chat-7b-v3-3) |
|
This is a quantized gguf version. |
|
|
|
# Open LLM Leaderboard Evaluation Results |
|
Base Model's Eval (better than [OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) btw) - https://huggingface.co/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp#open-llm-leaderboard-evaluation-results |
|
|
|
So, a bit worse but not too different. |
|
|
|
|