Mark-Arcee's picture
Update README.md
18c26ae verified
|
raw
history blame
1 kB
metadata
license: apache-2.0
tags:
  - merge
  - mergekit
  - mistralai/Mistral-7B-v0.1+predibase/customer_support
  - NousResearch/Nous-Hermes-2-Mistral-7B-DPO

Alpaca-Dragon-Smaug-Slerp

Alpaca-Dragon-Smaug-Slerp is a merge of the following models using mergekit:

🧩 Configuration

yaml_config = ''' slices: - sources: - model: ibivibiv/alpaca-dragon-72b-v1 layer_range: [0, 80] - model: abacusai/Smaug-72B-v0.1 layer_range: [0, 80] merge_method: slerp base_model: abacusai/Smaug-72B-v0.1 parameters: t: - filter: self_attn value: [0, 0.5, 0.3, 0.7, 1] - filter: mlp value: [1, 0.5, 0.7, 0.3, 0] - value: 0.5 dtype: bfloat16

'''