longthinker / README.md
c10x's picture
Upload folder using huggingface_hub
e1bb4a2 verified
|
raw
history blame
1.05 kB
metadata
base_model:
  - O1-OPEN/OpenO1-LLama-8B-v0.1
  - THUDM/LongWriter-llama3.1-8b
library_name: transformers
tags:
  - mergekit
  - merge

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using O1-OPEN/OpenO1-LLama-8B-v0.1 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: O1-OPEN/OpenO1-LLama-8B-v0.1
    parameters:
      density: 0.7
      weight: 0.7
  - model: THUDM/LongWriter-llama3.1-8b
    parameters:
      density: 0.3
      weight: 0.3

merge_method: ties
base_model: O1-OPEN/OpenO1-LLama-8B-v0.1
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16