Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
qwen3-4b-swegym-moto-kl02-multitrain-grpo-tfcov10-b04-lr1e6-s12-adapter – AI Model by imdatta0 | AlphaNeural AI
You can deploy this model and start earning money today!
imdatta0
/
qwen3-4b-swegym-moto-kl02-multitrain-grpo-tfcov10-b04-lr1e6-s12-adapter
like
0
peft
safetensors
qwen3
swe-gym
moto
lora
grpo
unsloth
text-generation
conversational
unsloth/Qwen3-4B-Instruct-2507
adapter
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Qwen3-4B SWE-Gym moto KL02 target-file coverage ablation adapter
This repository contains a PEFT LoRA adapter checkpoint from the Qwen3 SWE-Gym moto investigation.
Negative ablation: target-file coverage bonus did not improve held-out greedy over the inherited KL02 adapter.
Local source checkpoint before upload:
/mnt/disks/unslothai/datta0/cache/qwen3-grpo-patch/20260604_233602_swegym_q4b-kl02-multitrain-grpo-tfcov10-b04-lr1e6-s12_b90e3a9/checkpoints/best_holdout
Use with the base model unsloth/Qwen3-4B-Instruct-2507.
