Quantization made by Richard Erkhov.

mistral_2X7b - GGUF

Model creator: https://huggingface.co/tourist800/
Original model: https://huggingface.co/tourist800/mistral_2X7b/

Name	Quant method	Size
mistral_2X7b.Q2_K.gguf	Q2_K	2.53GB
mistral_2X7b.IQ3_XS.gguf	IQ3_XS	2.81GB
mistral_2X7b.IQ3_S.gguf	IQ3_S	2.96GB
mistral_2X7b.Q3_K_S.gguf	Q3_K_S	2.95GB
mistral_2X7b.IQ3_M.gguf	IQ3_M	3.06GB
mistral_2X7b.Q3_K.gguf	Q3_K	3.28GB
mistral_2X7b.Q3_K_M.gguf	Q3_K_M	3.28GB
mistral_2X7b.Q3_K_L.gguf	Q3_K_L	3.56GB
mistral_2X7b.IQ4_XS.gguf	IQ4_XS	3.67GB
mistral_2X7b.Q4_0.gguf	Q4_0	3.83GB
mistral_2X7b.IQ4_NL.gguf	IQ4_NL	3.87GB
mistral_2X7b.Q4_K_S.gguf	Q4_K_S	3.86GB
mistral_2X7b.Q4_K.gguf	Q4_K	4.07GB
mistral_2X7b.Q4_K_M.gguf	Q4_K_M	4.07GB
mistral_2X7b.Q4_1.gguf	Q4_1	4.24GB
mistral_2X7b.Q5_0.gguf	Q5_0	4.65GB
mistral_2X7b.Q5_K_S.gguf	Q5_K_S	4.65GB
mistral_2X7b.Q5_K.gguf	Q5_K	4.78GB
mistral_2X7b.Q5_K_M.gguf	Q5_K_M	4.78GB
mistral_2X7b.Q5_1.gguf	Q5_1	5.07GB
mistral_2X7b.Q6_K.gguf	Q6_K	5.53GB
mistral_2X7b.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 tags: - merge - mergekit - lazymergekit - mistralai/Mistral-7B-Instruct-v0.2 - mistralai/Mistral-7B-v0.1

Mistral_2X7b

Marcoro14-7B-slerp is a merge of the following models using mergekit:

🧩 Configuration

slices:
  - sources:
      - model: mistralai/Mistral-7B-Instruct-v0.2
        layer_range: [0, 32]
      - model: mistralai/Mistral-7B-v0.1
        layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-Instruct-v0.2
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