ermiaazarkhalili/Qwen3.8-4B-SFT-Fable5
046
Uploaded finetuned model
- Developed by: ermiaazarkhalili
- License: apache-2.0
- Finetuned from model : empero-ai/Qwen3.8-4B
This qwen3_5 model was trained 2x faster with Unsloth and Huggingface's TRL library.
This qwen3_5 model was trained 2x faster with Unsloth and Huggingface's TRL library.