40 lines
1.0 KiB
Markdown
40 lines
1.0 KiB
Markdown
---
|
|
license: agpl-3.0
|
|
language:
|
|
- en
|
|
---
|
|
|
|
# Michel - 13B
|
|
|
|
**A Uncensored fine tune model general tasks focused of [NousHermes-Llama2-13B](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b).**
|
|
With the help of [my team](https://huggingface.co/ConvexAI).
|
|
|
|
#### Quants
|
|
|
|
[Michel Exl2 Quant](https://huggingface.co/bartowski/Michel-13B-exl2)
|
|
[Michel GGUF Quant](https://huggingface.co/Kquant03/Michel-13B-GGUF)
|
|
|
|
### Useful
|
|
|
|
- **Uses Llama2 prompt template.**
|
|
- Next one will be more interesting :}
|
|
|
|
### I had good results with this parameters:
|
|
- temperature: 0.8
|
|
- top_p: 0.75
|
|
- min_p: 0
|
|
- top_k: 0
|
|
- repetition_penalty: 1.05
|
|
|
|
### General Usecase Test
|
|
|
|
|
|
### BenchMarks on OpenLLM Leaderboard
|
|
More details: [Michel-13B OpenLLM BenchMarks](https://huggingface.co/datasets/open-llm-leaderboard/details_PotatoOff__Michel-13B)
|
|
|
|
|
|
|
|
### Thank you h2m for the compute
|
|
|
|
### Have Fun :)
|