Quantization made by Richard Erkhov.

T3Q_SOLAR_DARETIES_v1.0 - GGUF

Model creator: https://huggingface.co/er1123090/
Original model: https://huggingface.co/er1123090/T3Q_SOLAR_DARETIES_v1.0/

Name	Quant method	Size
T3Q_SOLAR_DARETIES_v1.0.Q2_K.gguf	Q2_K	3.73GB
T3Q_SOLAR_DARETIES_v1.0.Q3_K_S.gguf	Q3_K_S	4.34GB
T3Q_SOLAR_DARETIES_v1.0.Q3_K.gguf	Q3_K	4.84GB
T3Q_SOLAR_DARETIES_v1.0.Q3_K_M.gguf	Q3_K_M	4.84GB
T3Q_SOLAR_DARETIES_v1.0.Q3_K_L.gguf	Q3_K_L	5.26GB
T3Q_SOLAR_DARETIES_v1.0.IQ4_XS.gguf	IQ4_XS	5.43GB
T3Q_SOLAR_DARETIES_v1.0.Q4_0.gguf	Q4_0	5.66GB
T3Q_SOLAR_DARETIES_v1.0.IQ4_NL.gguf	IQ4_NL	5.72GB
T3Q_SOLAR_DARETIES_v1.0.Q4_K_S.gguf	Q4_K_S	5.7GB
T3Q_SOLAR_DARETIES_v1.0.Q4_K.gguf	Q4_K	6.02GB
T3Q_SOLAR_DARETIES_v1.0.Q4_K_M.gguf	Q4_K_M	6.02GB
T3Q_SOLAR_DARETIES_v1.0.Q4_1.gguf	Q4_1	6.27GB
T3Q_SOLAR_DARETIES_v1.0.Q5_0.gguf	Q5_0	6.89GB
T3Q_SOLAR_DARETIES_v1.0.Q5_K_S.gguf	Q5_K_S	2.91GB
T3Q_SOLAR_DARETIES_v1.0.Q5_K.gguf	Q5_K	7.08GB
T3Q_SOLAR_DARETIES_v1.0.Q5_K_M.gguf	Q5_K_M	7.08GB
T3Q_SOLAR_DARETIES_v1.0.Q5_1.gguf	Q5_1	7.51GB
T3Q_SOLAR_DARETIES_v1.0.Q6_K.gguf	Q6_K	8.2GB
T3Q_SOLAR_DARETIES_v1.0.Q8_0.gguf	Q8_0	10.62GB

Original model description:

base_model: - T3Q-LLM/T3Q-LLM2-FP-v1.0 - hwkwon/S-SOLAR-10.7B-v1.5 - chihoonlee10/T3Q-ko-solar-dpo-v7.0 library_name: transformers tags: - mergekit - merge license: mit

Untitled Model (1)

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 T3Q-LLM/T3Q-LLM2-FP-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: hwkwon/S-SOLAR-10.7B-v1.5
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: chihoonlee10/T3Q-ko-solar-dpo-v7.0
    parameters:
      density: 0.5
      weight: [0, 0.3, 0.7, 1] # weight gradient
merge_method: dare_ties
base_model: T3Q-LLM/T3Q-LLM2-FP-v1.0
parameters:
  normalize: true
  int8_mask: true
dtype: float16

#mergekit-yaml /path/to/config.yml ./output/directory --cuda