Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
qwen3-8b-sva-codev2k-s42-lora – AI Model by mmoselhy077 | AlphaNeural AI
You can deploy this model and start earning money today!
mmoselhy077
/
qwen3-8b-sva-codev2k-s42-lora
like
0
peft
safetensors
systemverilog
sva
lora
qwen3
no-go
Qwen/Qwen3-8B
adapter
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
qwen3-8b-sva-codev2k-s42-lora
CodeV re-distill scale-up
+2k arm
(2093 CodeV rows, 78% of corpus). Qwen3-8B LoRA (r64/a128, 3ep). full-356 equiv pass@1 =
44.1%
—
NO-GO
(base922 baseline 51.5%). Regression is intrinsic to the CodeV distribution, not dilution.
LoRA adapter on
Qwen/Qwen3-8B
(load with PEFT). Recorded
negative result
. Champion:
mmoselhy077/qwen3-8b-sva-rest-r2-merged
(84.8% equiv@5).
