Downloads · 30 days
77
7% of all-time downloads
Silvelter_-_LumimaiMagPantheon-12B-gguf
RichardErkhov/Silvelter_-_LumimaiMagPantheon-12B-gguf
Silvelter_-_LumimaiMagPantheon-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
1.1K
Public
Repo size
124 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf147 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 27, 2024
- Updated
- Oct 27, 2024
- SHA
- 33f39dc6
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
LumimaiMagPantheon-12B - GGUF
- Model creator: https://huggingface.co/Silvelter/
- Original model: https://huggingface.co/Silvelter/LumimaiMagPantheon-12B/
| Name | Quant method | Size |
|---|---|---|
| LumimaiMagPantheon-12B.Q2_K.gguf | Q2_K | 4.46GB |
| LumimaiMagPantheon-12B.Q3_K_S.gguf | Q3_K_S | 5.15GB |
| LumimaiMagPantheon-12B.Q3_K.gguf | Q3_K | 5.67GB |
| LumimaiMagPantheon-12B.Q3_K_M.gguf | Q3_K_M | 5.67GB |
| LumimaiMagPantheon-12B.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| LumimaiMagPantheon-12B.IQ4_XS.gguf | IQ4_XS | 6.33GB |
| LumimaiMagPantheon-12B.Q4_0.gguf | Q4_0 | 6.59GB |
| LumimaiMagPantheon-12B.IQ4_NL.gguf | IQ4_NL | 6.65GB |
| LumimaiMagPantheon-12B.Q4_K_S.gguf | Q4_K_S | 6.63GB |
| LumimaiMagPantheon-12B.Q4_K.gguf | Q4_K | 6.96GB |
| LumimaiMagPantheon-12B.Q4_K_M.gguf | Q4_K_M | 6.96GB |
| LumimaiMagPantheon-12B.Q4_1.gguf | Q4_1 | 7.26GB |
| LumimaiMagPantheon-12B.Q5_0.gguf | Q5_0 | 7.93GB |
| LumimaiMagPantheon-12B.Q5_K_S.gguf | Q5_K_S | 7.93GB |
| LumimaiMagPantheon-12B.Q5_K.gguf | Q5_K | 8.13GB |
| LumimaiMagPantheon-12B.Q5_K_M.gguf | Q5_K_M | 8.13GB |
| LumimaiMagPantheon-12B.Q5_1.gguf | Q5_1 | 8.61GB |
| LumimaiMagPantheon-12B.Q6_K.gguf | Q6_K | 9.37GB |
| LumimaiMagPantheon-12B.Q8_0.gguf | Q8_0 | 12.13GB |
Original model description:
base_model:
- Undi95/Lumimaid-Magnum-12B
- Gryphe/Pantheon-RP-1.6-12b-Nemo library_name: transformers tags:
- mergekit
- merge
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the della merge method using Undi95/Lumimaid-Magnum-12B as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: Undi95/Lumimaid-Magnum-12B
parameters:
int8_mask: true
rescale: true
normalize: false
merge_method: della
dtype: bfloat16
models:
- model: Undi95/Lumimaid-Magnum-12B
parameters:
density: [0.4, 0.5, 0.6, 0.4, 0.6, 0.5, 0.4]
epsilon: [0.15, 0.15, 0.25, 0.15, 0.15]
lambda: 0.85
weight: [0.6, 0.5, 0.4, 0.6, 0.4, 0.5, 0.6]
- model: Gryphe/Pantheon-RP-1.6-12b-Nemo
parameters:
density: [0.45, 0.55, 0.45, 0.55, 0.45]
epsilon: [0.1, 0.1, 0.25, 0.1, 0.1]
lambda: 0.85
weight: [0.55, 0.45, 0.55, 0.45, 0.55]
- Created
- Oct 27, 2024
- Updated
- Oct 27, 2024