Quantization made by Richard Erkhov.

SyntheticMoist-11B-v2 - GGUF

Model creator: https://huggingface.co/v000000/
Original model: https://huggingface.co/v000000/SyntheticMoist-11B-v2/

Name	Quant method	Size
SyntheticMoist-11B-v2.Q2_K.gguf	Q2_K	3.73GB
SyntheticMoist-11B-v2.IQ3_XS.gguf	IQ3_XS	4.14GB
SyntheticMoist-11B-v2.IQ3_S.gguf	IQ3_S	4.37GB
SyntheticMoist-11B-v2.Q3_K_S.gguf	Q3_K_S	4.34GB
SyntheticMoist-11B-v2.IQ3_M.gguf	IQ3_M	4.51GB
SyntheticMoist-11B-v2.Q3_K.gguf	Q3_K	4.84GB
SyntheticMoist-11B-v2.Q3_K_M.gguf	Q3_K_M	4.84GB
SyntheticMoist-11B-v2.Q3_K_L.gguf	Q3_K_L	5.26GB
SyntheticMoist-11B-v2.IQ4_XS.gguf	IQ4_XS	5.43GB
SyntheticMoist-11B-v2.Q4_0.gguf	Q4_0	5.66GB
SyntheticMoist-11B-v2.IQ4_NL.gguf	IQ4_NL	5.72GB
SyntheticMoist-11B-v2.Q4_K_S.gguf	Q4_K_S	5.7GB
SyntheticMoist-11B-v2.Q4_K.gguf	Q4_K	6.02GB
SyntheticMoist-11B-v2.Q4_K_M.gguf	Q4_K_M	6.02GB
SyntheticMoist-11B-v2.Q4_1.gguf	Q4_1	6.27GB
SyntheticMoist-11B-v2.Q5_0.gguf	Q5_0	6.89GB
SyntheticMoist-11B-v2.Q5_K_S.gguf	Q5_K_S	6.89GB
SyntheticMoist-11B-v2.Q5_K.gguf	Q5_K	7.08GB
SyntheticMoist-11B-v2.Q5_K_M.gguf	Q5_K_M	7.08GB
SyntheticMoist-11B-v2.Q5_1.gguf	Q5_1	7.51GB
SyntheticMoist-11B-v2.Q6_K.gguf	Q6_K	8.2GB
SyntheticMoist-11B-v2.Q8_0.gguf	Q8_0	10.62GB

Original model description:

base_model: - Sao10K/Fimbulvetr-11B-v2 - TheDrummer/Moistral-11B-v3 - Himitsui/MedMitsu-Instruct-11B - Himitsui/Kaiju-11B - migtissera/Synthia-v3.0-11B - jeiku/Re-Host_Limarp_Mistral library_name: transformers tags: - mergekit - merge - solar - llama - not-for-all-audiences

SyntheticMoist-v2

RP Model, Solar. Higher density+LimaRP led to better performance, Use Alpaca/Vicuna.

Thanks mradermacher for the quants!

Quants

GGUF Q6_K

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 Sao10K/Fimbulvetr-11B-v2 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Himitsui/MedMitsu-Instruct-11B
    parameters:
      weight: 0.13
      density: 0.60
  - model: Himitsui/Kaiju-11B
    parameters:
      weight: 0.22
      density: 0.73
  - model: migtissera/Synthia-v3.0-11B+jeiku/Re-Host_Limarp_Mistral
    parameters:
      weight: 0.28
      density: 0.80
  - model: TheDrummer/Moistral-11B-v3
    parameters:
      weight: 0.37
      density: 0.85
merge_method: dare_ties
base_model: Sao10K/Fimbulvetr-11B-v2
parameters:
  int8_mask: true
dtype: bfloat16