metadata

base_model: []
library_name: transformers
tags:
  - mergekit
  - merge

POINTS-1-5-Qwen-2-5-7B-Chat

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:

/mnt/cephfs/bensenliu/wfs/weights/mm/mmq-llava-20241130e2-sft-pointsv15-hf/
/mnt/cephfs/bensenliu/wfs/weights/mm/mmq-llava-20241127e3-sft-pointsv15-hf/
/mnt/cephfs/bensenliu/wfs/weights/mm/mmq-llava-20241129e2-sft-pointsv15-hf/
/mnt/cephfs/bensenliu/wfs/weights/mm/mmq-llava-20241130e3-sft-pointsv15-hf/

Configuration

The following YAML configuration was used to produce this model:

models:
  # - model: /mnt/cephfs/bensenliu/wfs/weights/mm/mmq-llava-20241123e2-sft-hf/
  #   parameters:
  #     weight: 1.0
  # - model: /mnt/cephfs/bensenliu/wfs/weights/mm/mmq-llava-20241124e2-sft-hf/
  #   parameters:
  #     weight: 1.0
  # - model: /mnt/cephfs/bensenliu/wfs/weights/mm/mmq-llava-20241125e1-sft-hf/
  #   parameters:
  #     weight: 1.0
  # - model: /mnt/cephfs/bensenliu/wfs/weights/mm/mmq-llava-20241125e3-sft-hf/
  #   parameters:
  #     weight: 1.0
  # - model: /mnt/cephfs/bensenliu/wfs/weights/mm/mmq-llava-20241127e1-sft-hf/
  #   parameters:
  #     weight: 1.0
  # - model: /mnt/cephfs/bensenliu/wfs/weights/mm/mmq-llava-20241127e2-sft-hf/
  #   parameters:
  #     weight: 1.0
  - model: /mnt/cephfs/bensenliu/wfs/weights/mm/mmq-llava-20241127e3-sft-pointsv15-hf/
    parameters:
      weight: 1.0
  - model: /mnt/cephfs/bensenliu/wfs/weights/mm/mmq-llava-20241129e2-sft-pointsv15-hf/
    parameters:
      weight: 1.0
  - model: /mnt/cephfs/bensenliu/wfs/weights/mm/mmq-llava-20241130e2-sft-pointsv15-hf/
    parameters:
      weight: 1.0
  - model: /mnt/cephfs/bensenliu/wfs/weights/mm/mmq-llava-20241130e3-sft-pointsv15-hf/
    parameters:
      weight: 1.0
merge_method: linear
parameters:
  normalize: true
dtype: bfloat16