Downloads · 30 days
8
19% of all-time downloads
Qwen3.5-397B-A17B-LoRA-SFT-v1
JinnP/Qwen3.5-397B-A17B-LoRA-SFT-v1
Qwen3.5-397B-A17B-LoRA-SFT-v1 is a machine learning model from JinnP. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
LoRA adapter fine-tuned on AMD GPU kernel optimization agent trajectories. Superseded by v2.
All-time downloads
43
Public
Repo size
149 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors129 MB · 87%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Mar 20, 2026
- Updated
- Mar 20, 2026
- SHA
- 032f2f67
Base models
Model card
From the Hugging Face model README
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 Superseded by v2.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.
- Library
- peft
- License
- apache-2.0
- Created
- Mar 20, 2026
- Updated
- Mar 20, 2026