koesn/MonarchLake-7B-GGUF

MonarchLake-7B

Description

This repo contains GGUF format model files for MonarchLake-7B.

Files Provided

Name	Quant	Bits	File Size	Remark
monarchlake-7b.IQ3_XXS.gguf	IQ3_XXS	3	3.02 GB	3.06 bpw quantization
monarchlake-7b.IQ3_S.gguf	IQ3_S	3	3.18 GB	3.44 bpw quantization
monarchlake-7b.IQ3_M.gguf	IQ3_M	3	3.28 GB	3.66 bpw quantization mix
monarchlake-7b.Q4_0.gguf	Q4_0	4	4.11 GB	3.56G, +0.2166 ppl
monarchlake-7b.IQ4_NL.gguf	IQ4_NL	4	4.16 GB	4.25 bpw non-linear quantization
monarchlake-7b.Q4_K_M.gguf	Q4_K_M	4	4.37 GB	3.80G, +0.0532 ppl
monarchlake-7b.Q5_K_M.gguf	Q5_K_M	5	5.13 GB	4.45G, +0.0122 ppl
monarchlake-7b.Q6_K.gguf	Q6_K	6	5.94 GB	5.15G, +0.0008 ppl
monarchlake-7b.Q8_0.gguf	Q8_0	8	7.70 GB	6.70G, +0.0004 ppl

Parameters

path	type	architecture	rope_theta	sliding_win	max_pos_embed
macadeliccc/MonarchLake-7B	mistral	MistralForCausalLM	10000.0	4096	32768

Benchmarks

Original Model Card

MonarchLake-7B

This model equips AlphaMonarch-7B with a strong base of emotional intelligence.

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• macadeliccc/WestLake-7b-v2-laser-truthy-dpo
• mlabonne/AlphaMonarch-7B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: mlabonne/AlphaMonarch-7B
        layer_range: [0, 32]
      - model: macadeliccc/WestLake-7b-v2-laser-truthy-dpo
        layer_range: [0, 32]
merge_method: slerp
base_model: mlabonne/AlphaMonarch-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