Downloads · 30 days
51
2% of all-time downloads
RichardErkhov/MarinaraSpaghetti_-_Nemomix-v4.0-12B-gguf
MarinaraSpaghetti_-_Nemomix-v4.0-12B-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
51
2% of all-time downloads
All-time downloads
2.1K
Public
Repo size
141 GB
Likes
0
Public
Click a slice to open those files.
.gguf163 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Nemomix-v4.0-12B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Nemomix-v4.0-12B.Q2_K.gguf | Q2_K | 4.46GB |
| Nemomix-v4.0-12B.IQ3_XS.gguf | IQ3_XS | 4.94GB |
| Nemomix-v4.0-12B.IQ3_S.gguf | IQ3_S | 5.18GB |
| Nemomix-v4.0-12B.Q3_K_S.gguf | Q3_K_S | 5.15GB |
| Nemomix-v4.0-12B.IQ3_M.gguf | IQ3_M | 5.33GB |
| Nemomix-v4.0-12B.Q3_K.gguf | Q3_K | 5.67GB |
| Nemomix-v4.0-12B.Q3_K_M.gguf | Q3_K_M | 5.67GB |
| Nemomix-v4.0-12B.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| Nemomix-v4.0-12B.IQ4_XS.gguf | IQ4_XS | 6.33GB |
| Nemomix-v4.0-12B.Q4_0.gguf | Q4_0 | 6.59GB |
| Nemomix-v4.0-12B.IQ4_NL.gguf | IQ4_NL | 6.65GB |
| Nemomix-v4.0-12B.Q4_K_S.gguf | Q4_K_S | 6.63GB |
| Nemomix-v4.0-12B.Q4_K.gguf | Q4_K | 6.96GB |
| Nemomix-v4.0-12B.Q4_K_M.gguf | Q4_K_M | 6.96GB |
| Nemomix-v4.0-12B.Q4_1.gguf | Q4_1 | 7.26GB |
| Nemomix-v4.0-12B.Q5_0.gguf | Q5_0 | 7.93GB |
| Nemomix-v4.0-12B.Q5_K_S.gguf | Q5_K_S | 7.93GB |
| Nemomix-v4.0-12B.Q5_K.gguf | Q5_K | 8.13GB |
| Nemomix-v4.0-12B.Q5_K_M.gguf | Q5_K_M | 8.13GB |
| Nemomix-v4.0-12B.Q5_1.gguf | Q5_1 | 8.61GB |
| Nemomix-v4.0-12B.Q6_K.gguf | Q6_K | 9.37GB |
| Nemomix-v4.0-12B.Q8_0.gguf | Q8_0 | 12.13GB |
base_model: [] library_name: transformers tags:


My main goal is to merge the smartness of the base Instruct Nemo with the better prose from the different roleplaying fine-tunes. This one seems to be the best out of all, so far. All credits and thanks go to Intervitens, Mistralai, Invisietch, and NeverSleep for providing amazing models used in the merge.
Mistral Instruct.
<s>[INST] {system} [/INST] {assistant}</s>[INST] {user} [/INST]
Lower Temperature of 0.35 recommended, although I had luck with Temperatures above one (1.0-1.2) if you crank up the Min P (0.01-0.1). Run with base DRY of 0.8/1.75/2/0 and you're good to go.
You can use my custom context/instruct/parameters presets for the model from here.
https://huggingface.co/MarinaraSpaghetti/SillyTavern-Settings/tree/main
https://huggingface.co/MarinaraSpaghetti/Nemomix-v4.0-12B-GGUF
V1: https://huggingface.co/MarinaraSpaghetti/Nemomix-v1.0-12B
V2: https://huggingface.co/MarinaraSpaghetti/Nemomix-v2.0-12B
V3: https://huggingface.co/MarinaraSpaghetti/Nemomix-v3.0-12B
V4: https://huggingface.co/MarinaraSpaghetti/Nemomix-v4.0-12B
This is a merge of pre-trained language models created using mergekit.
This model was merged using the della_linear merge method using F:\mergekit\mistralaiMistral-Nemo-Base-2407 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: F:\mergekit\invisietch_Atlantis-v0.1-12B
parameters:
weight: 0.16
density: 0.4
- model: F:\mergekit\mistralaiMistral-Nemo-Instruct-2407
parameters:
weight: 0.23
density: 0.5
- model: F:\mergekit\NeverSleepHistorical_lumi-nemo-e2.0
parameters:
weight: 0.27
density: 0.6
- model: F:\mergekit\intervitens_mini-magnum-12b-v1.1
parameters:
weight: 0.34
density: 0.8
merge_method: della_linear
base_model: F:\mergekit\mistralaiMistral-Nemo-Base-2407
parameters:
epsilon: 0.05
lambda: 1
int8_mask: true
dtype: bfloat16