Quantization made by Richard Erkhov.

INEX16-7b - GGUF

Model creator: https://huggingface.co/MSL7/
Original model: https://huggingface.co/MSL7/INEX16-7b/

Name	Quant method	Size
INEX16-7b.Q2_K.gguf	Q2_K	2.53GB
INEX16-7b.IQ3_XS.gguf	IQ3_XS	2.81GB
INEX16-7b.IQ3_S.gguf	IQ3_S	2.96GB
INEX16-7b.Q3_K_S.gguf	Q3_K_S	2.95GB
INEX16-7b.IQ3_M.gguf	IQ3_M	3.06GB
INEX16-7b.Q3_K.gguf	Q3_K	3.28GB
INEX16-7b.Q3_K_M.gguf	Q3_K_M	3.28GB
INEX16-7b.Q3_K_L.gguf	Q3_K_L	3.56GB
INEX16-7b.IQ4_XS.gguf	IQ4_XS	3.67GB
INEX16-7b.Q4_0.gguf	Q4_0	3.83GB
INEX16-7b.IQ4_NL.gguf	IQ4_NL	3.87GB
INEX16-7b.Q4_K_S.gguf	Q4_K_S	3.86GB
INEX16-7b.Q4_K.gguf	Q4_K	4.07GB
INEX16-7b.Q4_K_M.gguf	Q4_K_M	4.07GB
INEX16-7b.Q4_1.gguf	Q4_1	4.24GB
INEX16-7b.Q5_0.gguf	Q5_0	4.65GB
INEX16-7b.Q5_K_S.gguf	Q5_K_S	4.65GB
INEX16-7b.Q5_K.gguf	Q5_K	4.78GB
INEX16-7b.Q5_K_M.gguf	Q5_K_M	4.78GB
INEX16-7b.Q5_1.gguf	Q5_1	5.07GB
INEX16-7b.Q6_K.gguf	Q6_K	5.53GB
INEX16-7b.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 tags: - merge - mergekit - lazymergekit - MSL7/INEX12-7b - liminerity/i

INEX-16

INEX-16 is a merge of the following models using mergekit:

🧩 Configuration

slices:
  - sources:
      - model: MSL7/INEX12-7b
        layer_range: [0, 32]
      - model: liminerity/i
        layer_range: [0, 32]
merge_method: slerp
base_model: MSL7/INEX12-7b
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