Modelpublic

RichardErkhov/tushar310_-_Hippy-AAI-7B-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes251downloads

Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Hippy-AAI-7B - GGUF

—Model creator: https://huggingface.co/tushar310/
—Original model: https://huggingface.co/tushar310/Hippy-AAI-7B/

Name	Quant method	Size
Hippy-AAI-7B.Q2_K.gguf	Q2_K	2.53GB
Hippy-AAI-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
Hippy-AAI-7B.IQ3_S.gguf	IQ3_S	2.96GB
Hippy-AAI-7B.Q3_K_S.gguf	Q3KS	2.95GB
Hippy-AAI-7B.IQ3_M.gguf	IQ3_M	3.06GB
Hippy-AAI-7B.Q3_K.gguf	Q3_K	3.28GB
Hippy-AAI-7B.Q3_K_M.gguf	Q3KM	3.28GB
Hippy-AAI-7B.Q3_K_L.gguf	Q3KL	3.56GB
Hippy-AAI-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
Hippy-AAI-7B.Q4_0.gguf	Q4_0	3.83GB
Hippy-AAI-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
Hippy-AAI-7B.Q4_K_S.gguf	Q4KS	3.86GB
Hippy-AAI-7B.Q4_K.gguf	Q4_K	4.07GB
Hippy-AAI-7B.Q4_K_M.gguf	Q4KM	4.07GB
Hippy-AAI-7B.Q4_1.gguf	Q4_1	4.24GB
Hippy-AAI-7B.Q5_0.gguf	Q5_0	4.65GB
Hippy-AAI-7B.Q5_K_S.gguf	Q5KS	4.65GB
Hippy-AAI-7B.Q5_K.gguf	Q5_K	4.78GB
Hippy-AAI-7B.Q5_K_M.gguf	Q5KM	4.78GB
Hippy-AAI-7B.Q5_1.gguf	Q5_1	5.07GB
Hippy-AAI-7B.Q6_K.gguf	Q6_K	5.53GB
Hippy-AAI-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description: --- license: apache-2.0 tags:

—merge
—mergekit
—lazymergekit
—EmbeddedLLM/Mistral-7B-Merge-14-v0.1
—liminerity/M7-7b ---

Hippy-AAI-7B

Hippy-AAI-7B is a merge of the following models using mergekit:

🧩 Configuration

yaml

slices:
  - sources:
      - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.1
        layer_range: [0, 32]
      - model: liminerity/M7-7b
        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