Downloads · 30 days
235
5% of all-time downloads
aetherwiing_-_MN-12B-Starcannon-v2-gguf
RichardErkhov/aetherwiing_-_MN-12B-Starcannon-v2-gguf
aetherwiing_-_MN-12B-Starcannon-v2-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
4.8K
Public
Repo size
126 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf133 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 4, 2024
- Updated
- Aug 5, 2024
- SHA
- 747f2a12
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
MN-12B-Starcannon-v2 - GGUF
- Model creator: https://huggingface.co/aetherwiing/
- Original model: https://huggingface.co/aetherwiing/MN-12B-Starcannon-v2/
| Name | Quant method | Size |
|---|---|---|
| MN-12B-Starcannon-v2.Q2_K.gguf | Q2_K | 4.46GB |
| MN-12B-Starcannon-v2.IQ3_XS.gguf | IQ3_XS | 4.94GB |
| MN-12B-Starcannon-v2.IQ3_S.gguf | IQ3_S | 5.18GB |
| MN-12B-Starcannon-v2.Q3_K_S.gguf | Q3_K_S | 5.15GB |
| MN-12B-Starcannon-v2.IQ3_M.gguf | IQ3_M | 5.33GB |
| MN-12B-Starcannon-v2.Q3_K.gguf | Q3_K | 5.67GB |
| MN-12B-Starcannon-v2.Q3_K_M.gguf | Q3_K_M | 5.67GB |
| MN-12B-Starcannon-v2.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| MN-12B-Starcannon-v2.IQ4_XS.gguf | IQ4_XS | 6.33GB |
| MN-12B-Starcannon-v2.Q4_0.gguf | Q4_0 | 6.59GB |
| MN-12B-Starcannon-v2.IQ4_NL.gguf | IQ4_NL | 6.65GB |
| MN-12B-Starcannon-v2.Q4_K_S.gguf | Q4_K_S | 6.63GB |
| MN-12B-Starcannon-v2.Q4_K.gguf | Q4_K | 3.56GB |
| MN-12B-Starcannon-v2.Q4_K_M.gguf | Q4_K_M | 3.16GB |
| MN-12B-Starcannon-v2.Q4_1.gguf | Q4_1 | 7.26GB |
| MN-12B-Starcannon-v2.Q5_0.gguf | Q5_0 | 5.94GB |
| MN-12B-Starcannon-v2.Q5_K_S.gguf | Q5_K_S | 2.99GB |
| MN-12B-Starcannon-v2.Q5_K.gguf | Q5_K | 0.52GB |
| MN-12B-Starcannon-v2.Q5_K_M.gguf | Q5_K_M | 5.73GB |
| MN-12B-Starcannon-v2.Q5_1.gguf | Q5_1 | 4.09GB |
| MN-12B-Starcannon-v2.Q6_K.gguf | Q6_K | 9.37GB |
| MN-12B-Starcannon-v2.Q8_0.gguf | Q8_0 | 12.13GB |
Original model description:
base_model:
- nothingiisreal/MN-12B-Celeste-V1.9
- intervitens/mini-magnum-12b-v1.1 library_name: transformers tags:
- mergekit
- merge license: apache-2.0
MN-12B-Starcannon-v2
This is a merge of pre-trained language models created using mergekit. Turned out to be a bit more Magnum-esque, but still is very creative, and writing style is pretty nice, even if some slop words appear time to time. Might be a good fit for people wanting more variety than Magnum has, and more verbose prose than Celeste v1.9 has. <br><br> Dynamic FP8 <br> Static GGUF (by Mradermacher) <br> EXL2 (by kingbri of RoyalLab)
Merge Details
Merge Method
This model was merged using the TIES merge method using nothingiisreal/MN-12B-Celeste-V1.9 as a base.
Merge fodder
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: intervitens/mini-magnum-12b-v1.1
parameters:
density: 0.3
weight: 0.5
- model: nothingiisreal/MN-12B-Celeste-V1.9
parameters:
density: 0.7
weight: 0.5
merge_method: ties
base_model: nothingiisreal/MN-12B-Celeste-V1.9
parameters:
normalize: true
int8_mask: true
dtype: bfloat16
- Created
- Aug 4, 2024
- Updated
- Aug 5, 2024