Downloads · 30 days
102
3% of all-time downloads
Undi95_-_Lumimaid-Magnum-12B-gguf
RichardErkhov/Undi95_-_Lumimaid-Magnum-12B-gguf
Undi95_-_Lumimaid-Magnum-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
3.4K
Public
Repo size
121 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf127 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 4, 2024
- Updated
- Aug 5, 2024
- SHA
- 63680177
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Lumimaid-Magnum-12B - GGUF
- Model creator: https://huggingface.co/Undi95/
- Original model: https://huggingface.co/Undi95/Lumimaid-Magnum-12B/
| Name | Quant method | Size |
|---|---|---|
| Lumimaid-Magnum-12B.Q2_K.gguf | Q2_K | 4.46GB |
| Lumimaid-Magnum-12B.IQ3_XS.gguf | IQ3_XS | 4.94GB |
| Lumimaid-Magnum-12B.IQ3_S.gguf | IQ3_S | 5.18GB |
| Lumimaid-Magnum-12B.Q3_K_S.gguf | Q3_K_S | 5.15GB |
| Lumimaid-Magnum-12B.IQ3_M.gguf | IQ3_M | 5.33GB |
| Lumimaid-Magnum-12B.Q3_K.gguf | Q3_K | 5.67GB |
| Lumimaid-Magnum-12B.Q3_K_M.gguf | Q3_K_M | 5.67GB |
| Lumimaid-Magnum-12B.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| Lumimaid-Magnum-12B.IQ4_XS.gguf | IQ4_XS | 6.33GB |
| Lumimaid-Magnum-12B.Q4_0.gguf | Q4_0 | 6.59GB |
| Lumimaid-Magnum-12B.IQ4_NL.gguf | IQ4_NL | 4.2GB |
| Lumimaid-Magnum-12B.Q4_K_S.gguf | Q4_K_S | 2.71GB |
| Lumimaid-Magnum-12B.Q4_K.gguf | Q4_K | 0.37GB |
| Lumimaid-Magnum-12B.Q4_K_M.gguf | Q4_K_M | 5.03GB |
| Lumimaid-Magnum-12B.Q4_1.gguf | Q4_1 | 7.26GB |
| Lumimaid-Magnum-12B.Q5_0.gguf | Q5_0 | 2.85GB |
| Lumimaid-Magnum-12B.Q5_K_S.gguf | Q5_K_S | 0.94GB |
| Lumimaid-Magnum-12B.Q5_K.gguf | Q5_K | 5.54GB |
| Lumimaid-Magnum-12B.Q5_K_M.gguf | Q5_K_M | 3.65GB |
| Lumimaid-Magnum-12B.Q5_1.gguf | Q5_1 | 8.61GB |
| Lumimaid-Magnum-12B.Q6_K.gguf | Q6_K | 9.37GB |
| Lumimaid-Magnum-12B.Q8_0.gguf | Q8_0 | 12.13GB |
Original model description:
base_model:
- mistralai/Mistral-Nemo-Instruct-2407
- NeverSleep/Lumimaid-v0.2-12B
- Undi95/LocalC-12B-e2.0
- intervitens/mini-magnum-12b-v1.1 library_name: transformers tags:
- mergekit
- merge
Merge of Lumimaid and Magnum as requested by some.
I used the new DELLA merge method in mergekit and added a finetune of Nemo only on Claude input, trained on 16k ctx, in the mix.
Prompt template: Mistral
<s>[INST] {input} [/INST] {output}</s>
- Created
- Aug 4, 2024
- Updated
- Aug 5, 2024