Files
Qwen2.5-7B-hh-rlhf-sft/README.md
ModelHub XC 1df86c61f0 初始化项目,由ModelHub XC社区提供模型
Model: heli-stand/Qwen2.5-7B-hh-rlhf-sft
Source: Original Platform
2026-08-24 07:39:16 +08:00

31 lines
637 B
Markdown

---
library_name: transformers
tags:
- qwen2.5
- hh-rlhf
---
# Model Card for SFT Model Fine-tuned on hh-rlhf Dataset from Qwen2.5-7B
This model is supervised fine-tuned from Qwen2.5-7B based on the anthropic helpfulness-harmlessness rlhf datasets.
### Model Sources
- **Repository:** https://huggingface.co/Qwen/Qwen2.5-7B
## Training Procedure
### Training Data
- **Repository:** https://huggingface.co/datasets/heli-stand/hh-rlhf
### Training Hyperparameters
- **Optimizer:** Adamw
- **Learning Rate:** 1e-5
- **Batch Size:** 128
- **Epochs:** 1
- **Max_Length:** 1024
## Evaluation Results
- **Best Evaluation Loss:** 1.678