Hugging Face's logo

rawsh
/
mirrorqwen2.5-0.5b-SimPO

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
cpo
unsloth
text-generation-inference
Model card Files Community
rawsh commited on
Commit
7799d54
·
verified ·
1 Parent(s): 5e4de6c

Model save

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/dankgpt/huggingface/runs/3cgj46ws)
31
 
32
  This model was trained with CPO, a method introduced in [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://huggingface.co/papers/2401.08417).
33
 
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/dankgpt/huggingface/runs/tsy83cdb)
31
 
32
  This model was trained with CPO, a method introduced in [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://huggingface.co/papers/2401.08417).
33