hybrid_play_slerp

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:

• StephenZhu/SWE-Play-7B-mix
• synthetic-code-training/qwen25-coder-7b-loc441-514-func1183-gen480-5e-0-00005lr-bs8-bf16

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: synthetic-code-training/qwen25-coder-7b-loc441-514-func1183-gen480-5e-0-00005lr-bs8-bf16
        layer_range: [0, 28]
      - model: StephenZhu/SWE-Play-7B-mix
        layer_range: [0, 28]
# or, the equivalent models: syntax:
# models:
#   - model: psmathur/orca_mini_v3_13b
#   - model: garage-bAInd/Platypus2-13B
merge_method: slerp
base_model: synthetic-code-training/qwen25-coder-7b-loc441-514-func1183-gen480-5e-0-00005lr-bs8-bf16
parameters:
  t: 0.2
dtype: bfloat16