YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
SyntheticMoist-11B - GGUF
- Model creator: https://huggingface.co/v000000/
- Original model: https://huggingface.co/v000000/SyntheticMoist-11B/
Name | Quant method | Size |
---|---|---|
SyntheticMoist-11B.Q2_K.gguf | Q2_K | 3.73GB |
SyntheticMoist-11B.IQ3_XS.gguf | IQ3_XS | 4.14GB |
SyntheticMoist-11B.IQ3_S.gguf | IQ3_S | 4.37GB |
SyntheticMoist-11B.Q3_K_S.gguf | Q3_K_S | 4.34GB |
SyntheticMoist-11B.IQ3_M.gguf | IQ3_M | 4.51GB |
SyntheticMoist-11B.Q3_K.gguf | Q3_K | 4.84GB |
SyntheticMoist-11B.Q3_K_M.gguf | Q3_K_M | 4.84GB |
SyntheticMoist-11B.Q3_K_L.gguf | Q3_K_L | 5.26GB |
SyntheticMoist-11B.IQ4_XS.gguf | IQ4_XS | 5.43GB |
SyntheticMoist-11B.Q4_0.gguf | Q4_0 | 5.66GB |
SyntheticMoist-11B.IQ4_NL.gguf | IQ4_NL | 5.72GB |
SyntheticMoist-11B.Q4_K_S.gguf | Q4_K_S | 5.7GB |
SyntheticMoist-11B.Q4_K.gguf | Q4_K | 6.02GB |
SyntheticMoist-11B.Q4_K_M.gguf | Q4_K_M | 6.02GB |
SyntheticMoist-11B.Q4_1.gguf | Q4_1 | 6.27GB |
SyntheticMoist-11B.Q5_0.gguf | Q5_0 | 6.89GB |
SyntheticMoist-11B.Q5_K_S.gguf | Q5_K_S | 6.89GB |
SyntheticMoist-11B.Q5_K.gguf | Q5_K | 7.08GB |
SyntheticMoist-11B.Q5_K_M.gguf | Q5_K_M | 7.08GB |
SyntheticMoist-11B.Q5_1.gguf | Q5_1 | 7.51GB |
SyntheticMoist-11B.Q6_K.gguf | Q6_K | 8.2GB |
SyntheticMoist-11B.Q8_0.gguf | Q8_0 | 10.62GB |
Original model description:
base_model: - Himitsui/Kaiju-11B - TheDrummer/Moistral-11B-v3 - Himitsui/MedMitsu-Instruct-11B - upstage/SOLAR-10.7B-v1.0 - migtissera/Synthia-v3.0-11B library_name: transformers tags: - mergekit - merge - solar - llama - not-for-all-audiences
RP Model, Experimental Solar merge. Alpaca/Vicuna format.
Thanks mradermacher for the quants
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the DARE TIES merge method using upstage/SOLAR-10.7B-v1.0 as a base.
Models Merged
The following models were included in the merge:
- Himitsui/Kaiju-11B
- TheDrummer/Moistral-11B-v3
- Himitsui/MedMitsu-Instruct-11B
- migtissera/Synthia-v3.0-11B
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Himitsui/MedMitsu-Instruct-11B
parameters:
weight: 0.16
density: 0.42
- model: Himitsui/Kaiju-11B
parameters:
weight: 0.22
density: 0.54
- model: migtissera/Synthia-v3.0-11B
parameters:
weight: 0.28
density: 0.66
- model: TheDrummer/Moistral-11B-v3
parameters:
weight: 0.34
density: 0.78
merge_method: dare_ties
base_model: upstage/SOLAR-10.7B-v1.0
parameters:
int8_mask: true
dtype: bfloat16
- Downloads last month
- 24