RichardErkhov/tlphams_-_solar-10.7b-merged-v0.1-gguf

Quantization made by Richard Erkhov.

solar-10.7b-merged-v0.1 - GGUF

Model creator: https://huggingface.co/tlphams/
Original model: https://huggingface.co/tlphams/solar-10.7b-merged-v0.1/

Name	Quant method	Size
solar-10.7b-merged-v0.1.Q2_K.gguf	Q2_K	3.73GB
solar-10.7b-merged-v0.1.IQ3_XS.gguf	IQ3_XS	4.14GB
solar-10.7b-merged-v0.1.IQ3_S.gguf	IQ3_S	4.37GB
solar-10.7b-merged-v0.1.Q3_K_S.gguf	Q3_K_S	4.34GB
solar-10.7b-merged-v0.1.IQ3_M.gguf	IQ3_M	4.51GB
solar-10.7b-merged-v0.1.Q3_K.gguf	Q3_K	4.84GB
solar-10.7b-merged-v0.1.Q3_K_M.gguf	Q3_K_M	4.84GB
solar-10.7b-merged-v0.1.Q3_K_L.gguf	Q3_K_L	5.26GB
solar-10.7b-merged-v0.1.IQ4_XS.gguf	IQ4_XS	5.43GB
solar-10.7b-merged-v0.1.Q4_0.gguf	Q4_0	5.66GB
solar-10.7b-merged-v0.1.IQ4_NL.gguf	IQ4_NL	5.72GB
solar-10.7b-merged-v0.1.Q4_K_S.gguf	Q4_K_S	5.7GB
solar-10.7b-merged-v0.1.Q4_K.gguf	Q4_K	6.02GB
solar-10.7b-merged-v0.1.Q4_K_M.gguf	Q4_K_M	6.02GB
solar-10.7b-merged-v0.1.Q4_1.gguf	Q4_1	6.27GB
solar-10.7b-merged-v0.1.Q5_0.gguf	Q5_0	6.89GB
solar-10.7b-merged-v0.1.Q5_K_S.gguf	Q5_K_S	6.89GB
solar-10.7b-merged-v0.1.Q5_K.gguf	Q5_K	7.08GB
solar-10.7b-merged-v0.1.Q5_K_M.gguf	Q5_K_M	7.08GB
solar-10.7b-merged-v0.1.Q5_1.gguf	Q5_1	7.51GB
solar-10.7b-merged-v0.1.Q6_K.gguf	Q6_K	8.2GB
solar-10.7b-merged-v0.1.Q8_0.gguf	Q8_0	10.62GB

Original model description:

license: cc-by-nc-sa-4.0 tags: - merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using upstage/SOLAR-10.7B-v1.0 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: chihoonlee10/T3Q-ko-solar-dpo-v5.0
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: hyeogi/SOLAR-10.7B-v1.6
    parameters:
      density: 0.5
      weight: [0, 0.3, 0.7, 1] # weight gradient
  - model: krevas/SOLAR-10.7B
    parameters:
      density: 0.33
      weight:
        - filter: mlp
          value: 0.5
        - value: 0
merge_method: ties
base_model: upstage/SOLAR-10.7B-v1.0
parameters:
  normalize: true
  int8_mask: true
dtype: float16