Downloads · 30 days
22
19% of all-time downloads
PotatoOff_-_Michel-13B-gguf
RichardErkhov/PotatoOff_-_Michel-13B-gguf
PotatoOff_-_Michel-13B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
113
Public
Repo size
3.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf3.5 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 11, 2024
- Updated
- Aug 11, 2024
- SHA
- b15f3824
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Michel-13B - GGUF
- Model creator: https://huggingface.co/PotatoOff/
- Original model: https://huggingface.co/PotatoOff/Michel-13B/
| Name | Quant method | Size |
|---|---|---|
| Michel-13B.Q2_K.gguf | Q2_K | 3.12GB |
| Michel-13B.IQ3_XS.gguf | IQ3_XS | 0.16GB |
| Michel-13B.IQ3_S.gguf | IQ3_S | 0.0GB |
| Michel-13B.Q3_K_S.gguf | Q3_K_S | 0.0GB |
| Michel-13B.IQ3_M.gguf | IQ3_M | 0.0GB |
| Michel-13B.Q3_K.gguf | Q3_K | 0.0GB |
| Michel-13B.Q3_K_M.gguf | Q3_K_M | 0.0GB |
| Michel-13B.Q3_K_L.gguf | Q3_K_L | 0.0GB |
| Michel-13B.IQ4_XS.gguf | IQ4_XS | 0.0GB |
| Michel-13B.Q4_0.gguf | Q4_0 | 0.0GB |
| Michel-13B.IQ4_NL.gguf | IQ4_NL | 0.0GB |
| Michel-13B.Q4_K_S.gguf | Q4_K_S | 0.0GB |
| Michel-13B.Q4_K.gguf | Q4_K | 0.0GB |
| Michel-13B.Q4_K_M.gguf | Q4_K_M | 0.0GB |
| Michel-13B.Q4_1.gguf | Q4_1 | 0.0GB |
| Michel-13B.Q5_0.gguf | Q5_0 | 0.0GB |
| Michel-13B.Q5_K_S.gguf | Q5_K_S | 0.0GB |
| Michel-13B.Q5_K.gguf | Q5_K | 0.0GB |
| Michel-13B.Q5_K_M.gguf | Q5_K_M | 0.0GB |
| Michel-13B.Q5_1.gguf | Q5_1 | 0.0GB |
| Michel-13B.Q6_K.gguf | Q6_K | 0.0GB |
| Michel-13B.Q8_0.gguf | Q8_0 | 0.0GB |
Original model description:
license: agpl-3.0 language:
- en
Michel - 13B
A Uncensored fine tune model general tasks focused of NousHermes-Llama2-13B.
With the help of my team.
Quants
Michel Exl2 Quant
Michel GGUF Quant
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
Thank you h2m for the compute
Have Fun :)
- Created
- Aug 11, 2024
- Updated
- Aug 11, 2024