Quantization made by Richard Erkhov.

Saul-Instruct-Clown-7b - GGUF

Model creator: https://huggingface.co/arcee-ai/
Original model: https://huggingface.co/arcee-ai/Saul-Instruct-Clown-7b/

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

Original model description:

license: apache-2.0 tags: - merge - mergekit - CorticalStack/pastiche-crown-clown-7b-dare-dpo - Equall/Saul-Instruct-v1

Saul-Instruct-Clown-7b

Saul-Instruct-Clown-7b is a merge of the following models using mergekit:

🏆 Evaluation

OpenLLM

Saul-Instruct-Clown-7b OpenLLM benchmark suite

Model	Average	arc	HellaSwag	mmlu	TruthfulQA	gsm8k
arcee-ai/Saul-Instruct-Clown-7b	72.79	68.26	86.28	63.12	64.68	83.43

🧩 Configuration

  slices:
    - sources:
        - model: CorticalStack/pastiche-crown-clown-7b-dare-dpo
          layer_range: [0, 32]
        - model: Equall/Saul-Instruct-v1
          layer_range: [0, 32]
  merge_method: slerp
  base_model: CorticalStack/pastiche-crown-clown-7b-dare-dpo
  parameters:
    t:
      - filter: self_attn
        value: [0, 0.5, 0.3, 0.7, 1]
      - filter: mlp
        value: [1, 0.5, 0.7, 0.3, 0]
      - value: 0.5
  dtype: bfloat16