Downloads · 30 days
99
6% of all-time downloads
Slomb_-_MN-CelesteGold-12B-Merge-gguf
RichardErkhov/Slomb_-_MN-CelesteGold-12B-Merge-gguf
Slomb_-_MN-CelesteGold-12B-Merge-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
1.6K
Public
Repo size
123 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf145 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 29, 2024
- Updated
- Oct 30, 2024
- SHA
- beab8d9c
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
MN-CelesteGold-12B-Merge - GGUF
- Model creator: https://huggingface.co/Slomb/
- Original model: https://huggingface.co/Slomb/MN-CelesteGold-12B-Merge/
| Name | Quant method | Size |
|---|---|---|
| MN-CelesteGold-12B-Merge.Q2_K.gguf | Q2_K | 3.14GB |
| MN-CelesteGold-12B-Merge.Q3_K_S.gguf | Q3_K_S | 5.15GB |
| MN-CelesteGold-12B-Merge.Q3_K.gguf | Q3_K | 5.67GB |
| MN-CelesteGold-12B-Merge.Q3_K_M.gguf | Q3_K_M | 5.67GB |
| MN-CelesteGold-12B-Merge.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| MN-CelesteGold-12B-Merge.IQ4_XS.gguf | IQ4_XS | 6.33GB |
| MN-CelesteGold-12B-Merge.Q4_0.gguf | Q4_0 | 6.59GB |
| MN-CelesteGold-12B-Merge.IQ4_NL.gguf | IQ4_NL | 6.65GB |
| MN-CelesteGold-12B-Merge.Q4_K_S.gguf | Q4_K_S | 6.63GB |
| MN-CelesteGold-12B-Merge.Q4_K.gguf | Q4_K | 6.96GB |
| MN-CelesteGold-12B-Merge.Q4_K_M.gguf | Q4_K_M | 6.96GB |
| MN-CelesteGold-12B-Merge.Q4_1.gguf | Q4_1 | 7.26GB |
| MN-CelesteGold-12B-Merge.Q5_0.gguf | Q5_0 | 7.93GB |
| MN-CelesteGold-12B-Merge.Q5_K_S.gguf | Q5_K_S | 7.93GB |
| MN-CelesteGold-12B-Merge.Q5_K.gguf | Q5_K | 8.13GB |
| MN-CelesteGold-12B-Merge.Q5_K_M.gguf | Q5_K_M | 8.13GB |
| MN-CelesteGold-12B-Merge.Q5_1.gguf | Q5_1 | 8.61GB |
| MN-CelesteGold-12B-Merge.Q6_K.gguf | Q6_K | 9.37GB |
| MN-CelesteGold-12B-Merge.Q8_0.gguf | Q8_0 | 12.13GB |
Original model description:
base_model:
- nothingiisreal/MN-12B-Celeste-V1.9
- elinas/Chronos-Gold-12B-1.0 library_name: transformers tags:
- mergekit
- merge
merge
This is a merge of pre-trained language models created using mergekit.
A combination of the two most promising models for roleplay chatbots as of 08/26/2024. I am not affiliated with any of the models used in the merge.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: elinas/Chronos-Gold-12B-1.0
layer_range:
- 0
- 40
- model: nothingiisreal/MN-12B-Celeste-V1.9
layer_range:
- 0
- 40
merge_method: slerp
base_model: elinas/Chronos-Gold-12B-1.0
parameters:
t:
- filter: self_attn
value:
- 0
- 0.5
- 0.3
- 0.7
- 1
- filter: mlp
value:
- 1
- 0.5
- 0.7
- 0.3
- 0
- value: 0.5
dtype: bfloat16
- Created
- Oct 29, 2024
- Updated
- Oct 30, 2024