初始化项目,由ModelHub XC社区提供模型
Model: thu-ml/STAIR-Qwen2-7B-DPO-3 Source: Original Platform
This commit is contained in:
BIN
training_rewards_accuracies.png
Normal file
BIN
training_rewards_accuracies.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 40 KiB |
Reference in New Issue
Block a user