Downloads · 30 days
110
10% of all-time downloads
RichardErkhov/Sao10K_-_Fimbulvetr-10.7B-v1-gguf
Sao10K_-_Fimbulvetr-10.7B-v1-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.
Downloads · 30 days
110
10% of all-time downloads
All-time downloads
1.1K
Public
Repo size
122 GB
Likes
0
Public
Click a slice to open those files.
.gguf141 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Fimbulvetr-10.7B-v1 - GGUF
| Name | Quant method | Size |
|---|---|---|
| Fimbulvetr-10.7B-v1.Q2_K.gguf | Q2_K | 3.73GB |
| Fimbulvetr-10.7B-v1.IQ3_XS.gguf | IQ3_XS | 4.14GB |
| Fimbulvetr-10.7B-v1.IQ3_S.gguf | IQ3_S | 4.37GB |
| Fimbulvetr-10.7B-v1.Q3_K_S.gguf | Q3_K_S | 4.34GB |
| Fimbulvetr-10.7B-v1.IQ3_M.gguf | IQ3_M | 4.51GB |
| Fimbulvetr-10.7B-v1.Q3_K.gguf | Q3_K | 4.84GB |
| Fimbulvetr-10.7B-v1.Q3_K_M.gguf | Q3_K_M | 4.84GB |
| Fimbulvetr-10.7B-v1.Q3_K_L.gguf | Q3_K_L | 5.26GB |
| Fimbulvetr-10.7B-v1.IQ4_XS.gguf | IQ4_XS | 5.43GB |
| Fimbulvetr-10.7B-v1.Q4_0.gguf | Q4_0 | 5.66GB |
| Fimbulvetr-10.7B-v1.IQ4_NL.gguf | IQ4_NL | 5.72GB |
| Fimbulvetr-10.7B-v1.Q4_K_S.gguf | Q4_K_S | 5.7GB |
| Fimbulvetr-10.7B-v1.Q4_K.gguf | Q4_K | 6.02GB |
| Fimbulvetr-10.7B-v1.Q4_K_M.gguf | Q4_K_M | 6.02GB |
| Fimbulvetr-10.7B-v1.Q4_1.gguf | Q4_1 | 6.27GB |
| Fimbulvetr-10.7B-v1.Q5_0.gguf | Q5_0 | 6.89GB |
| Fimbulvetr-10.7B-v1.Q5_K_S.gguf | Q5_K_S | 6.89GB |
| Fimbulvetr-10.7B-v1.Q5_K.gguf | Q5_K | 7.08GB |
| Fimbulvetr-10.7B-v1.Q5_K_M.gguf | Q5_K_M | 7.08GB |
| Fimbulvetr-10.7B-v1.Q5_1.gguf | Q5_1 | 7.51GB |
| Fimbulvetr-10.7B-v1.Q6_K.gguf | Q6_K | 8.2GB |
| Fimbulvetr-10.7B-v1.Q8_0.gguf | Q8_0 | 10.62GB |
license: cc-by-nc-4.0 language:
My current low-budget daily driver, so far.
Frostwindv2 + Sensualize v1.1 + ___ data on uncen Instruct Solar.
This is meant to be a verbose, smart Roleplaying model. I think I captured those two parts this time. Well, for my own cards and scenarios anyway, it passed with flying colours.
I recommend using min-p, I liked Universal-Light preset in SillyTavern.
Experimental.
### Instruction:
<Prompt>
### Input:
<Insert Context Here>
### Response:
forgot to link GGUF quants here: https://huggingface.co/Sao10K/Fimbulvetr-10.7B-v1-GGUF
or thebloke already quantized them to gptq and others. lonestriker did exl2 quants so ty ty a lot.
anyway, I have a few solar-based ideas before I move to the new InternLM, Yi, Mixtral or back to 70B.