Evathene-v1.2 / README.md
sophosympatheia's picture
Upload model weights (#1)
667f68f verified
|
raw
history blame
1.13 kB
metadata
base_model: []
library_name: transformers
tags:
  - mergekit
  - merge

evathene-v1.4

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 /home/llm/mergequant/models/BASE/Qwen_Qwen2.5-72B as a base.

Models Merged

The following models were included in the merge:

  • /home/llm/mergequant/models/BASE/Nexusflow_Athene-V2-Chat
  • /home/llm/mergequant/models/BASE/EVA-UNIT-01_EVA-Qwen2.5-72B-v0.1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /home/llm/mergequant/models/BASE/EVA-UNIT-01_EVA-Qwen2.5-72B-v0.1
    parameters:
      weight: 1
      density: 1
  - model: /home/llm/mergequant/models/BASE/Nexusflow_Athene-V2-Chat
    parameters:
      weight: [0.0, 0.2, 0.66, 0.8, 1.0, 0.8, 0.66, 0.2, 0.0]
      density: 0.5
merge_method: ties
base_model: /home/llm/mergequant/models/BASE/Qwen_Qwen2.5-72B
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16