Project-Angel2
Collection
The collections is the new version of Project-Angel following the DeepSeek fine-tune training method with a refined dataset.
•
6 items
•
Updated
Uploaded model
- Developed by: derek33125
- License: apache-2.0
- Finetuned from model : unsloth/DeepSeek-R1-Distill-Qwen-7B
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
Dataset
- EmoLLM
- SoulChat Multi-Trun Dataset
- Train: Val = 240,000: 24,000
- Since those datasets are both in simplified Chinese, using this model in other languages may encounter performance drops.
- Downloads last month
- 56
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support