Downloads · 30 days
5
12% of all-time downloads
Pablo-Flores-Mollinedo/verilog-qwen2.5-coder-7b-v11-v9-repair-distilled-direct-lora
verilog-qwen2.5-coder-7b-v11-v9-repair-distilled-direct-lora is a text generation model from Pablo-Flores-Mollinedo. Use it when you need the model to write or continue text. It is set up for peft.
LoRA adapter trained from v9 using v9 + v7b repair-loop passing outputs distilled to direct spec - code rows.
Downloads · 30 days
5
12% of all-time downloads
All-time downloads
43
Public
Repo size
334 MB
Likes
0
Public
Click a slice to open those files.
.safetensors323 MB · 97%
From the Hugging Face model README
LoRA adapter trained from v9 using v9 + v7b repair-loop passing outputs distilled to direct spec -> code rows.
VerilogEval v2 direct:
This regressed vs v9 direct (67/156). Use v9 as default direct adapter. This repo is kept as an experiment artifact.
Pipeline that generated the distillation data:
Caveat: benchmark-targeted; not clean zero-shot leaderboard evidence.