Downloads · 30 days
20
2% of all-time downloads
Wonda-Qwen3-14B-nt-V2-gt2-e3
idopinto/Wonda-Qwen3-14B-nt-V2-gt2-e3
Wonda-Qwen3-14B-nt-V2-gt2-e3 is a text generation model from idopinto. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Full fine-tune of Qwen/Qwen3-14B on the WONDA loop-invariant generation task.
All-time downloads
823
Public
Parameters
14.8B
88.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors29.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Mar 27, 2026
- Updated
- Jun 21, 2026
- SHA
- 50f796a7
Try a prompt
Base models
Model card
From the Hugging Face model README
Wonda-Qwen3-14B-nt-V2-gt2-e3
Full fine-tune of Qwen/Qwen3-14B on the WONDA loop-invariant generation task.
| Setting | Value |
|---|---|
| Dataset | WONDA V2 (quality_grade >= 2) |
| Training | Full fine-tune (no LoRA), 3 epochs |
| Task | Generate inductive loop invariants for C programs |
Legacy name: idopinto/qwen3-14b-full-nt-gen-inv-sft-v2-g2-e3 (same weights).
Quick start
from transformers import pipeline
generator = pipeline(
"text-generation",
model="idopinto/Wonda-Qwen3-14B-nt-V2-gt2-e3",
device="cuda",
)
See the Wonda repository for evaluation and training details.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Created
- Mar 27, 2026
- Updated
- Jun 21, 2026