R3-Qwen3-14B_merged_linear_6model

Name: R3-Qwen3-14B_merged_linear_6model
Availability: InStock

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:

HLeiTR/qwen3_14b_full_5k_ckpt_45
rubricreward/R3-Qwen3-14B-LoRA-5K-v1.1
rubricreward/R3-Qwen3-14B-14k
HLeiTR/qwen3_14b_full_15k_ckpt_125
rubricreward/R3-Qwen3-14B-4k
rubricreward/R3-Qwen3-14B-LoRA-4k

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: rubricreward/R3-Qwen3-14B-LoRA-4k
    parameters:
      weight: 0.2
  - model: rubricreward/R3-Qwen3-14B-4k
    parameters:
      weight: 0.15
  - model: rubricreward/R3-Qwen3-14B-14k
    parameters:
      weight: 0.15
  - model: rubricreward/R3-Qwen3-14B-LoRA-5K-v1.1
    parameters:
      weight: 0.2
  - model: HLeiTR/qwen3_14b_full_5k_ckpt_45
    parameters:
      weight: 0.15
  - model: HLeiTR/qwen3_14b_full_15k_ckpt_125
    parameters:
      weight: 0.15
merge_method: linear
dtype: bfloat16

rubricreward/R3-Qwen3-14B_merged_linear_6model

R3-Qwen3-14B_merged_linear_6model

Merge Details

Merge Method

Models Merged

Configuration

rubricreward/
R3-Qwen3-14B_merged_linear_6model