Text Generation
Transformers
Safetensors
English
Chinese
llama
conversational
Inference Endpoints
text-generation-inference
Faro-Yi-34B-DPO / README.md
wenbopan's picture
Upload folder using huggingface_hub
dc5be82 verified
metadata
base_model: []
library_name: transformers
tags:
  - mergekit
  - merge

Faro-34B-Slerp

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

  • /cephfs/panwenbo/work/models/Faro-34B-DPO
  • /cephfs/panwenbo/work/models/Faro-34B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /cephfs/panwenbo/work/models/Faro-34B-DPO
  - model: /cephfs/panwenbo/work/models/Faro-34B
merge_method: slerp
base_model: /cephfs/panwenbo/work/models/Faro-34B
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 # fallback for rest of tensors
dtype: bfloat16