Hugging Face's logo

RichardErkhov
/
CorticalStack_-_shadow-clown-7B-slerp-gguf

GGUF
Model card Files
xet
 Community

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

shadow-clown-7B-slerp - GGUF

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

Original model description:

license: apache-2.0 tags: - merge - mergekit - Gille/StrangeMerges_32-7B-slerp - yam-peleg/Experiment26-7B

Shadow clown logo

shadow-clown-7B-slerp

shadow-clown-7B-slerp is a DARE merge of the following models using mergekit:

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

🧩 Configuration 

slices:
  - sources:
      - model: CorticalStack/pastiche-crown-clown-7b-dare-dpo
        layer_range: [0, 32]
      - model: MSL7/INEX12-7b
        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

slices:
  - sources:
      - model: liminerity/M7-7b
        layer_range: [0, 32]
      - model: CorticalStack/pastiche-crown-clown-7b-dare-dpo
        layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/M7-7b
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


slices:
  - sources:
      - model: ammarali32/multi_verse_model
        layer_range: [0, 32]
      - model: liminerity/merge
        layer_range: [0, 32]
merge_method: slerp
base_model: ammarali32/multi_verse_model
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


slices:
  - sources:
      - model: Gille/StrangeMerges_32-7B-slerp
        layer_range: [0, 32]
      - model: yam-peleg/Experiment26-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: Gille/StrangeMerges_32-7B-slerp
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
Downloads last month
76
GGUF
Model size
7B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for RichardErkhov/CorticalStack_-_shadow-clown-7B-slerp-gguf