Downloads · 30 days
14
12% of all-time downloads
Qwen3.5-9B-aerialsim-rl-step100
maya-multimodal/Qwen3.5-9B-aerialsim-rl-step100
Qwen3.5-9B-aerialsim-rl-step100 is a reinforcement learning model from maya-multimodal. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Qwen3.5-9B fine-tuned with GRPO on the aerialsim-env 17-family aerial safety scenario mix, trained via prime-rl on a 4x H100 pod. This is the step-100 checkpoint from run smoke17familyqwen359b4gpuwide2026-07-15.
All-time downloads
119
Public
Parameters
9.4B
18.8 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors18.8 GB · 100%
At a glance
- Task
- Reinforcement Learning
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_5
- Access
- Public
- Created
- Jul 16, 2026
- Updated
- Jul 16, 2026
- SHA
- deaa1ff5
Base models
Model card
From the Hugging Face model README
Qwen3.5-9B-aerialsim-rl-step100
Qwen3.5-9B fine-tuned with GRPO on the aerialsim-env 17-family aerial safety scenario mix, trained via prime-rl on a 4x H100 pod. This is the step-100 checkpoint from run smoke_17family_qwen35_9b_4gpu_wide_2026-07-15.
Training summary
- Base: Qwen/Qwen3.5-9B (dense multimodal,
qwen3_5arch) - Environment: aerialsim-env v0.1, Cosys-AirSim / UE5.5 Blocks scene, 17 scenario families
- Observation mode:
both(RGB frame + text scaffold withlanding_zone_clear,obstacle_ahead,distance_to_goal, waypoints) - Reward: binary success on terminal action
- Algorithm: GRPO, batch_size=4, group_size=4
- Optimizer: AdamW with CPU offload, lr=5e-7
- Rollout sampler: temperature=0.3, max_completion_tokens=1024
- Eval sampler: temperature=0.0
- Sequence length: 4096
- GPU split: 2 train + 2 infer, tensor_parallel=2 on each side
- Steps: 100
Evaluation
Per-family deterministic (T=0, single decode) eval with scaffolded text state is pending; will be reported in the accompanying paper.
Intended use
Research on visual-grounded aerial safety decisions and RL fine-tuning of multimodal LLMs on simulated aerial mission scenarios.
Author
Nahid Alam (@nahidalam) — Maya Multimodal
- Task
- Reinforcement Learning
- Library
- transformers
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Jul 16, 2026
- Updated
- Jul 16, 2026