Downloads · 30 days
85
4% of all-time downloads
RichardErkhov/Darkknight535_-_Moonlight-L3-15B-v2-64k-gguf
Darkknight535_-_Moonlight-L3-15B-v2-64k-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
85
4% of all-time downloads
All-time downloads
2.4K
Public
Repo size
139 GB
Likes
0
Public
Click a slice to open those files.
.gguf166 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Moonlight-L3-15B-v2-64k - GGUF
| Name | Quant method | Size |
|---|---|---|
| Moonlight-L3-15B-v2-64k.Q2_K.gguf | Q2_K | 5.35GB |
| Moonlight-L3-15B-v2-64k.Q3_K_S.gguf | Q3_K_S | 6.21GB |
| Moonlight-L3-15B-v2-64k.Q3_K.gguf | Q3_K | 6.87GB |
| Moonlight-L3-15B-v2-64k.Q3_K_M.gguf | Q3_K_M | 6.87GB |
| Moonlight-L3-15B-v2-64k.Q3_K_L.gguf | Q3_K_L | 5.16GB |
| Moonlight-L3-15B-v2-64k.IQ4_XS.gguf | IQ4_XS | 2.8GB |
| Moonlight-L3-15B-v2-64k.Q4_0.gguf | Q4_0 | 3.31GB |
| Moonlight-L3-15B-v2-64k.IQ4_NL.gguf | IQ4_NL | 8.08GB |
| Moonlight-L3-15B-v2-64k.Q4_K_S.gguf | Q4_K_S | 8.05GB |
| Moonlight-L3-15B-v2-64k.Q4_K.gguf | Q4_K | 8.48GB |
| Moonlight-L3-15B-v2-64k.Q4_K_M.gguf | Q4_K_M | 8.48GB |
| Moonlight-L3-15B-v2-64k.Q4_1.gguf | Q4_1 | 8.84GB |
| Moonlight-L3-15B-v2-64k.Q5_0.gguf | Q5_0 | 9.68GB |
| Moonlight-L3-15B-v2-64k.Q5_K_S.gguf | Q5_K_S | 9.68GB |
| Moonlight-L3-15B-v2-64k.Q5_K.gguf | Q5_K | 9.93GB |
| Moonlight-L3-15B-v2-64k.Q5_K_M.gguf | Q5_K_M | 9.93GB |
| Moonlight-L3-15B-v2-64k.Q5_1.gguf | Q5_1 | 10.53GB |
| Moonlight-L3-15B-v2-64k.Q6_K.gguf | Q6_K | 11.48GB |
| Moonlight-L3-15B-v2-64k.Q8_0.gguf | Q8_0 | 14.86GB |
library_name: transformers tags:

Default llama3 instruct and context preset, but here is the one i use. Instruct Context
Temp : 1.2
Min P : 0.01
Repetition Penalty : 1.05
OR
Dry 0.7, 1.75, 2,0
XTC 0.1, 0.5
[And everything else neutral]
Temp : 0.6 - 0.8
Min P : 0.1
Repetition Penalty : 1.1
OR
Dry 1, 1.75, 2,0
XTC 0.1, 0.2
[And everything else neutral]
Develop the plot slowly, always stay in character. Describe all actions in full, elaborate, explicit, graphic, and vivid detail. Mention all relevant sensory perceptions. Keep the story immersive and engaging. Speak as other person when needed and prefix with the name of person you're speaking as except {{user}}.