Downloads · 30 days
3
1% of all-time downloads
RichardErkhov/922CA_-_Moniphi-3-v1-gguf
922CA_-_Moniphi-3-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
3
1% of all-time downloads
All-time downloads
316
Public
Repo size
43.5 GB
Likes
0
Public
Click a slice to open those files.
.gguf50.4 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Moniphi-3-v1 - GGUF
| Name | Quant method | Size |
|---|---|---|
| Moniphi-3-v1.Q2_K.gguf | Q2_K | 1.35GB |
| Moniphi-3-v1.IQ3_XS.gguf | IQ3_XS | 1.49GB |
| Moniphi-3-v1.IQ3_S.gguf | IQ3_S | 1.57GB |
| Moniphi-3-v1.Q3_K_S.gguf | Q3_K_S | 1.57GB |
| Moniphi-3-v1.IQ3_M.gguf | IQ3_M | 1.65GB |
| Moniphi-3-v1.Q3_K.gguf | Q3_K | 1.75GB |
| Moniphi-3-v1.Q3_K_M.gguf | Q3_K_M | 1.75GB |
| Moniphi-3-v1.Q3_K_L.gguf | Q3_K_L | 1.9GB |
| Moniphi-3-v1.IQ4_XS.gguf | IQ4_XS | 1.93GB |
| Moniphi-3-v1.Q4_0.gguf | Q4_0 | 2.03GB |
| Moniphi-3-v1.IQ4_NL.gguf | IQ4_NL | 2.04GB |
| Moniphi-3-v1.Q4_K_S.gguf | Q4_K_S | 2.04GB |
| Moniphi-3-v1.Q4_K.gguf | Q4_K | 2.16GB |
| Moniphi-3-v1.Q4_K_M.gguf | Q4_K_M | 2.16GB |
| Moniphi-3-v1.Q4_1.gguf | Q4_1 | 2.24GB |
| Moniphi-3-v1.Q5_0.gguf | Q5_0 | 2.46GB |
| Moniphi-3-v1.Q5_K_S.gguf | Q5_K_S | 2.46GB |
| Moniphi-3-v1.Q5_K.gguf | Q5_K | 2.53GB |
| Moniphi-3-v1.Q5_K_M.gguf | Q5_K_M | 2.53GB |
| Moniphi-3-v1.Q5_1.gguf | Q5_1 | 2.68GB |
| Moniphi-3-v1.Q6_K.gguf | Q6_K | 2.92GB |
| Moniphi-3-v1.Q8_0.gguf | Q8_0 | 3.78GB |
language:
This is meant to be mainly a chat model with limited RP ability.
For best results: replace "Human" and "Assistant" with "Player" and "Monika" like so:
\nPlayer: (prompt)\nMonika:
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
This model is meant to closely reflect the characteristics of Monika. Despite this, there is always the chance that "Monika" will hallucinate and get information about herself wrong or act out of character (especially for a model of this size).
Finally, this model is not guaranteed to output aligned or safe outputs, use at your own risk!