Downloads · 30 days
96
4% of all-time downloads
ParasiticRogue_-_Magnum-Instruct-12B-gguf
RichardErkhov/ParasiticRogue_-_Magnum-Instruct-12B-gguf
ParasiticRogue_-_Magnum-Instruct-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.
All-time downloads
2.6K
Public
Repo size
141 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf163 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 17, 2024
- Updated
- Sep 17, 2024
- SHA
- b0c5b32c
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Magnum-Instruct-12B - GGUF
- Model creator: https://huggingface.co/ParasiticRogue/
- Original model: https://huggingface.co/ParasiticRogue/Magnum-Instruct-12B/
| Name | Quant method | Size |
|---|---|---|
| Magnum-Instruct-12B.Q2_K.gguf | Q2_K | 4.46GB |
| Magnum-Instruct-12B.IQ3_XS.gguf | IQ3_XS | 4.94GB |
| Magnum-Instruct-12B.IQ3_S.gguf | IQ3_S | 5.18GB |
| Magnum-Instruct-12B.Q3_K_S.gguf | Q3_K_S | 5.15GB |
| Magnum-Instruct-12B.IQ3_M.gguf | IQ3_M | 5.33GB |
| Magnum-Instruct-12B.Q3_K.gguf | Q3_K | 5.67GB |
| Magnum-Instruct-12B.Q3_K_M.gguf | Q3_K_M | 5.67GB |
| Magnum-Instruct-12B.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| Magnum-Instruct-12B.IQ4_XS.gguf | IQ4_XS | 6.33GB |
| Magnum-Instruct-12B.Q4_0.gguf | Q4_0 | 6.59GB |
| Magnum-Instruct-12B.IQ4_NL.gguf | IQ4_NL | 6.65GB |
| Magnum-Instruct-12B.Q4_K_S.gguf | Q4_K_S | 6.63GB |
| Magnum-Instruct-12B.Q4_K.gguf | Q4_K | 6.96GB |
| Magnum-Instruct-12B.Q4_K_M.gguf | Q4_K_M | 6.96GB |
| Magnum-Instruct-12B.Q4_1.gguf | Q4_1 | 7.26GB |
| Magnum-Instruct-12B.Q5_0.gguf | Q5_0 | 7.93GB |
| Magnum-Instruct-12B.Q5_K_S.gguf | Q5_K_S | 7.93GB |
| Magnum-Instruct-12B.Q5_K.gguf | Q5_K | 8.13GB |
| Magnum-Instruct-12B.Q5_K_M.gguf | Q5_K_M | 8.13GB |
| Magnum-Instruct-12B.Q5_1.gguf | Q5_1 | 8.61GB |
| Magnum-Instruct-12B.Q6_K.gguf | Q6_K | 9.37GB |
| Magnum-Instruct-12B.Q8_0.gguf | Q8_0 | 12.13GB |
Original model description:
base_model:
- mistralai/Mistral-Nemo-Instruct-2407
- intervitens/mini-magnum-12b-v1.1 license: apache-2.0 library_name: transformers tags:
- merge
- roleplay
- not-for-all-audiences
Magnum-Instruct-12B
Simple della_linear merge done at a 50/50 split with high density using Mini-Magnum and Nemo Instruct. Nothing fancy to it, really. Seems good on both intelligence and creativity so far.
Big thanks to the MistralAI and Anthracite/SillyTilly teams for the models used!
GGUF quants made by mradermacher:
https://huggingface.co/mradermacher/Magnum-Instruct-12B-GGUF
Settings
Temperature @ 0.7
Min-P @ 0.02
Smoothing Factor @ 0.3
Smoothing Curve @ 1.5
DRY Multiplier (plus standard DRY settings) @ 0.8
Skip Special Tokens @ On
Everything else @ Off
Prompt Format: Nemo-Mistral
[INST] user prompt[/INST] character response</s>[INST] user prompt[/INST]
Models Merged
The following models were included in the merge:
- Created
- Sep 17, 2024
- Updated
- Sep 17, 2024