R1-JSON / README.md
mergekit-uploader's picture
Upload folder using huggingface_hub
1c9365d verified
metadata
base_model:
  - >-
    MasterControlAIML/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured
  - mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1
library_name: transformers
tags:
  - mergekit
  - merge

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1
        layer_range: [0, 28]
      - model: MasterControlAIML/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured
        layer_range: [0, 28]
merge_method: slerp
base_model: mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1
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