Qwen3.5-397B-A17B LoRA SFT Adapter (v1 - 16K, naive chunks)
LoRA adapter fine-tuned on AMD GPU kernel optimization agent trajectories. Superseded by v2.
| Metric | Value |
|---|---|
| Final train loss | 0.1628 |
| cutoff_len | 16,384 |
| Training examples | 1,133 (naive 5-turn chunks) |
| Epochs | 3 (18 steps) |
| Runtime | 57 min |
See v2 adapter for the improved version.
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for JinnP/Qwen3.5-397B-A17B-LoRA-SFT-v1
Base model
Qwen/Qwen3.5-397B-A17B