Downloads · 30 days
62
2% of all-time downloads
RichardErkhov/Sao10K_-_Solstice-11B-v1-gguf
Sao10K_-_Solstice-11B-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
62
2% of all-time downloads
All-time downloads
2.9K
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.
Solstice-11B-v1 - GGUF
| Name | Quant method | Size |
|---|---|---|
| Solstice-11B-v1.Q2_K.gguf | Q2_K | 3.73GB |
| Solstice-11B-v1.IQ3_XS.gguf | IQ3_XS | 4.14GB |
| Solstice-11B-v1.IQ3_S.gguf | IQ3_S | 4.37GB |
| Solstice-11B-v1.Q3_K_S.gguf | Q3_K_S | 4.34GB |
| Solstice-11B-v1.IQ3_M.gguf | IQ3_M | 4.51GB |
| Solstice-11B-v1.Q3_K.gguf | Q3_K | 4.84GB |
| Solstice-11B-v1.Q3_K_M.gguf | Q3_K_M | 4.84GB |
| Solstice-11B-v1.Q3_K_L.gguf | Q3_K_L | 5.26GB |
| Solstice-11B-v1.IQ4_XS.gguf | IQ4_XS | 5.43GB |
| Solstice-11B-v1.Q4_0.gguf | Q4_0 | 5.66GB |
| Solstice-11B-v1.IQ4_NL.gguf | IQ4_NL | 5.72GB |
| Solstice-11B-v1.Q4_K_S.gguf | Q4_K_S | 5.7GB |
| Solstice-11B-v1.Q4_K.gguf | Q4_K | 6.02GB |
| Solstice-11B-v1.Q4_K_M.gguf | Q4_K_M | 6.02GB |
| Solstice-11B-v1.Q4_1.gguf | Q4_1 | 6.27GB |
| Solstice-11B-v1.Q5_0.gguf | Q5_0 | 6.89GB |
| Solstice-11B-v1.Q5_K_S.gguf | Q5_K_S | 6.89GB |
| Solstice-11B-v1.Q5_K.gguf | Q5_K | 7.08GB |
| Solstice-11B-v1.Q5_K_M.gguf | Q5_K_M | 7.08GB |
| Solstice-11B-v1.Q5_1.gguf | Q5_1 | 7.51GB |
| Solstice-11B-v1.Q6_K.gguf | Q6_K | 8.2GB |
| Solstice-11B-v1.Q8_0.gguf | Q8_0 | 10.62GB |
license: cc-by-nc-4.0 language:
===== Solstice-11B-v1 =====
A model trained with the sole goal of NSFW.
That is it.
Results are to be as expected.
Finetuned off several instruct datasets that are NSFW. Example subset Below, other instruct datasets modified are private for now. Outputs were manually verified by me and two good friends.
Lewd-Assistant-v1 ---> Used a combination of Claude 2.0, GPT-4-Turbo and WinterGoddess-1.4x to reformat instead of a small 10B model [Fimbulvetr-v1] like the example dataset shown, which resulted in less errors and better answers. Private for now.
Ruled Out names: <br>Solarslut <br>Solascivious <br>Sultry <br>Sundress <br>Scorch
Prompt Format: Alpaca
There are several issues with the model, but this is an experimental one so :shrug: <br>----> May speak as {{user}} sometimes. I know what causes it. I kinda like it though that way. <br>----> May ramble on or give small outputs. Sampler settings. <br>----> May be a little inconsistent at times. Yeah its inevitable due to the nature of the data. <br>----> Steers towards NSFW --> As Expected.
GGUF: https://huggingface.co/Sao10K/Solstice-11B-v1-GGUF
exl2: https://huggingface.co/models?search=LoneStriker%20Solstice-11B-v1
thanks to lonestriker for the quants