RichardErkhov/CorticalStack_-_pastiche-crown-clown-7b-dare-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

pastiche-crown-clown-7b-dare - GGUF

• Model creator: https://huggingface.co/CorticalStack/
• Original model: https://huggingface.co/CorticalStack/pastiche-crown-clown-7b-dare/

Name	Quant method	Size
pastiche-crown-clown-7b-dare.Q2_K.gguf	Q2_K	2.53GB
pastiche-crown-clown-7b-dare.IQ3_XS.gguf	IQ3_XS	2.81GB
pastiche-crown-clown-7b-dare.IQ3_S.gguf	IQ3_S	2.96GB
pastiche-crown-clown-7b-dare.Q3_K_S.gguf	Q3_K_S	2.95GB
pastiche-crown-clown-7b-dare.IQ3_M.gguf	IQ3_M	3.06GB
pastiche-crown-clown-7b-dare.Q3_K.gguf	Q3_K	3.28GB
pastiche-crown-clown-7b-dare.Q3_K_M.gguf	Q3_K_M	3.28GB
pastiche-crown-clown-7b-dare.Q3_K_L.gguf	Q3_K_L	3.56GB
pastiche-crown-clown-7b-dare.IQ4_XS.gguf	IQ4_XS	3.67GB
pastiche-crown-clown-7b-dare.Q4_0.gguf	Q4_0	3.83GB
pastiche-crown-clown-7b-dare.IQ4_NL.gguf	IQ4_NL	3.87GB
pastiche-crown-clown-7b-dare.Q4_K_S.gguf	Q4_K_S	3.86GB
pastiche-crown-clown-7b-dare.Q4_K.gguf	Q4_K	4.07GB
pastiche-crown-clown-7b-dare.Q4_K_M.gguf	Q4_K_M	4.07GB
pastiche-crown-clown-7b-dare.Q4_1.gguf	Q4_1	4.24GB
pastiche-crown-clown-7b-dare.Q5_0.gguf	Q5_0	4.65GB
pastiche-crown-clown-7b-dare.Q5_K_S.gguf	Q5_K_S	4.65GB
pastiche-crown-clown-7b-dare.Q5_K.gguf	Q5_K	4.78GB
pastiche-crown-clown-7b-dare.Q5_K_M.gguf	Q5_K_M	4.78GB
pastiche-crown-clown-7b-dare.Q5_1.gguf	Q5_1	5.07GB
pastiche-crown-clown-7b-dare.Q6_K.gguf	Q6_K	5.53GB
pastiche-crown-clown-7b-dare.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 tags: - merge - mergekit - bardsai/jaskier-7b-dpo-v5.6 - mlabonne/AlphaMonarch-7B - mlabonne/NeuralMonarch-7B - macadeliccc/MBX-7B-v3-DPO

pastiche-crown-clown-7B-dare

pastiche-crown-clown-7B-dare is a DARE merge of the following models using mergekit:

• bardsai/jaskier-7b-dpo-v5.6
• mlabonne/AlphaMonarch-7B
• mlabonne/NeuralMonarch-7B
• macadeliccc/MBX-7B-v3-DPO

See the paper Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch for more on the method.

🧩 Configuration

models:
  - model: bardsai/jaskier-7b-dpo-v5.6
  - model: mlabonne/AlphaMonarch-7B
    parameters:
      density: 0.53
      weight: 0.2
  - model: mlabonne/NeuralMonarch-7B
    parameters:
      density: 0.53
      weight: 0.4
  - model: macadeliccc/MBX-7B-v3-DPO
    parameters:
      density: 0.53
      weight: 0.4
merge_method: dare_ties
base_model: bardsai/jaskier-7b-dpo-v5.6
parameters:
  int8_mask: true
dtype: bfloat16