v000000/Qwen2.5-14B-Gutenberg-0.25e-Early

Qwen2.5-14B-Instruct Gutenberg DPO

• Early checkpoint_test 1/4: Qwen/Qwen2.5-14B-Instruct finetuned (DPO) on jondurbin/gutenberg-dpo-v0.1 for 0.25 epoch, 1.5e-5 learning rate.

Story writing, novel writing, RP, instruct

merge

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• Qwen/Qwen2.5-14B-Instruct + v000000/DPO_LORA_0.25

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/Qwen2.5-14B-Instruct+v000000/DPO_LORA_0.25
    parameters:
      weight: 1.0
merge_method: linear
dtype: bfloat16