Downloads · 30 days
0
qwen2.5-coder-14b-qasm-lora
QlyApp/qwen2.5-coder-14b-qasm-lora
qwen2.5-coder-14b-qasm-lora is a machine learning model from QlyApp. 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 mlx. The card lists the license as mit.
LoRA adapters from three fine-tuning rounds attempting to improve Qwen2.5-Coder-14B-Instruct (4-bit MLX) at OpenQASM circuit generation, trained and evaluated with qcbench / qicode on the verified-openqasm-circuits
Access
Public
Updated Jul 22, 2026
Repo size
91.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors91.8 MB · 100%
At a glance
- Library
- mlx
- License
- mit
- Access
- Public
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026
- SHA
- ee6be562
Base models
Model card
From the Hugging Face model README
Qwen2.5-Coder-14B QASM LoRA adapters (three rounds, honest null results)
LoRA adapters from three fine-tuning rounds attempting to improve Qwen2.5-Coder-14B-Instruct (4-bit MLX) at OpenQASM circuit generation, trained and evaluated with qcbench / qicode on the verified-openqasm-circuits dataset.
Headline: all three rounds are benchmark-neutral. Verified-rate on the qcbench extended suite is unchanged in every configuration (identical verified problem sets); validation loss converges to ~0.02-0.06 while circuit correctness does not move — the adapters learn the corpus style, not circuit semantics. We publish them because negative results with a clean instrument are worth more than silent failure.
| round | data | trainer | benchmark effect |
|---|---|---|---|
| 1 | 300 template pairs | QLoRA, 8 layers | none |
| 2 | 1,000 template pairs | QLoRA, 16 layers | none |
| 3 | 136 teacher solutions + 19 repair trajectories (4×) | QLoRA, 8 layers, max-seq 1792 | none |
Use with MLX: mlx_lm.server --model mlx-community/Qwen2.5-Coder-14B-Instruct-4bit --adapter-path round3/
Open question these adapters motivate: does FP16 higher-capacity SFT or verified-reward RL (GRPO on qcbench's dense scores) break this ceiling? That experiment needs GPU compute.
- Library
- mlx
- License
- mit
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026