Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
Qwen3-32B-NL2Bash-31step – AI Model by laion | AlphaNeural AI
You can deploy this model and start earning money today!
laion
/
Qwen3-32B-NL2Bash-31step
like
0
transformers
safetensors
qwen3
text-generation
reinforcement-learning
code
nl2bash
rl
terminal
conversational
en
DCAgent2/nl2bash-tasks-cleaned-oracle
Qwen/Qwen3-32B
finetune
apache-2.0
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Qwen3-32B-NL2Bash-31step
RL-trained Qwen3-32B on NL2Bash terminal tasks.
Training Details
Base model
:
Qwen/Qwen3-32B
Training method
: RLOO (async)
Training data
: 1,570 NL2Bash tasks (
DCAgent2/nl2bash-tasks-cleaned-oracle
)
Steps
: 31 global steps (3 epochs)
Infrastructure
: 17x4 GH200 GPU nodes (JSC), FSDP2 with TP=2 for inference engines (26 inference engines + 4 policy/ref nodes)
Sandbox environment
: Beta9/Beam containers for code execution
Batch size
: 64, 8 samples per prompt
Learning rate
: 1e-5
Training Curve
Metric
Step 1
Step 10
Step 20
Step 31
Avg Raw Reward
0.214
0.314
0.416
0.264
Pass@8
0.563
0.563
0.594
0.422
License
Apache 2.0
