Fredithefish/RewardModel

reward_model

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using ChaiML/reward_models_100_170000000_cp_498032 as a base.

Models Merged

The following models were included in the merge:

• WendyHoang/reward-model
• Fredithefish/ChaiReward-gpt2
• anhnv125/reward-model-v3

Configuration

The following YAML configuration was used to produce this model:

models:
- model: Fredithefish/ChaiReward-gpt2
  parameters:
    density: 0.5
    weight: 0.5
- model: anhnv125/reward-model-v3
  parameters:
    density: 0.5
    weight: 0.6
- model: WendyHoang/reward-model
  parameters:
    density: 0.5
    weight: 0.5

base_model: ChaiML/reward_models_100_170000000_cp_498032
merge_method: dare_ties
parameters:
  normalize: 1.0