Modelpublic

nlpguy/Qwen3.8-27B-Fimi-3

sourceHugging Faceupdated 1mo agoView on Hugging Face

2likes94downloads

Model Card

Fimi 3

This is a merge of pre-trained language models created using mergekit.

Use Fimi 2 for better agentic performance

Merge Details

Merge Method

This model was merged using the Reinforced Agent Merging Plus (Tensor-Local) merge method using Qwen/Qwen3.5-27B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

base_model: Qwen/Qwen3.5-27B
chat_template: qwen
dtype: bfloat16
merge_method: ramplus_tl
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 0]
        model: Danielbrdz/Barcenas-Qwen3.8-27B-Fable
      - layer_range: [0, 0]
        model: DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1
      - layer_range: [0, 0]
        model: DavidAU/Qwen3.6-27B-V1.1-FF711-Darker-Hero-GAIN-H2.0
      - layer_range: [0, 0]
        model: beyoru/Kiwen1.1-27B
      - layer_range: [0, 0]
        model: empero-ai/Qwythos-27B-v1
      - layer_range: [0, 0]
        model: bottlecapai/ThinkingCap-Qwen3.6-27B
      - layer_range: [0, 0]
        model: TeichAI/Qwen3.8-27B-Fable-Distill
      - layer_range: [0, 0]
        model: Qwen/Qwen3.5-27B
  model.language_model.layers:
    slices:
    - sources:
      - layer_range: [0, 64]
        model: Danielbrdz/Barcenas-Qwen3.8-27B-Fable
      - layer_range: [0, 64]
        model: DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1
      - layer_range: [0, 64]
        model: DavidAU/Qwen3.6-27B-V1.1-FF711-Darker-Hero-GAIN-H2.0
      - layer_range: [0, 64]
        model: beyoru/Kiwen1.1-27B
      - layer_range: [0, 64]
        model: empero-ai/Qwythos-27B-v1
      - layer_range: [0, 64]
        model: bottlecapai/ThinkingCap-Qwen3.6-27B
      - layer_range: [0, 64]
        model: TeichAI/Qwen3.8-27B-Fable-Distill
      - layer_range: [0, 64]
        model: Qwen/Qwen3.5-27B
  model.visual.blocks:
    slices:
    - sources:
      - layer_range: [0, 27]
        model: Danielbrdz/Barcenas-Qwen3.8-27B-Fable
      - layer_range: [0, 27]
        model: DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1
      - layer_range: [0, 27]
        model: DavidAU/Qwen3.6-27B-V1.1-FF711-Darker-Hero-GAIN-H2.0
      - layer_range: [0, 27]
        model: beyoru/Kiwen1.1-27B
      - layer_range: [0, 27]
        model: empero-ai/Qwythos-27B-v1
      - layer_range: [0, 27]
        model: bottlecapai/ThinkingCap-Qwen3.6-27B
      - layer_range: [0, 27]
        model: TeichAI/Qwen3.8-27B-Fable-Distill
      - layer_range: [0, 27]
        model: Qwen/Qwen3.5-27B
out_dtype: bfloat16
parameters:
  r: 0.25