Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
qwen3-4b-medrect-mixed-r2 – AI Model by Abdine | AlphaNeural AI
You can deploy this model and start earning money today!
Abdine
/
qwen3-4b-medrect-mixed-r2
like
0
transformers
safetensors
qwen3
text-generation
medserl
self-play
reinforcement-learning
Qwen/Qwen3-4B
finetune
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Abdine/qwen3-4b-medrect-mixed-r2
Round-1 MedSeRL self-play actor exported from VERL training.
Base model:
Qwen/Qwen3-4B
Training recipe: batched injector -> assessor self-play
Export path:
outputs/local_training/medrect_mixed_v2_merged
This artifact is intended for evaluation and manual testing.