Downloads · 30 days
10
10% of all-time downloads
Qwen3-4B-GRPO-Browser-Agent
mariocde/Qwen3-4B-GRPO-Browser-Agent
Qwen3-4B-GRPO-Browser-Agent is a machine learning model from mariocde. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
GRPO-trained Qwen3-4B for on-device browser agent (TinyBrowser/Wiegand).
All-time downloads
104
Public
Repo size
2.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf2.4 GB · 89%
At a glance
- Access
- Public
- Created
- Mar 24, 2026
- Updated
- Mar 24, 2026
- SHA
- 4efd836e
Model card
From the Hugging Face model README
Qwen3-4B GRPO Browser Agent
GRPO-trained Qwen3-4B for on-device browser agent (TinyBrowser/Wiegand).
Training
- GRPO: 20 iterations, group_size=8, reward 5.12→7.25, JSON validity 95%→100%
- Duration: 83 minutes on Tinker GPU cluster
- Rewards: valid_json(3x), correct_action(2x), element_exists(1.5x), task_progress(1x), length(0.5x)
Files
qwen3-4b-grpo-q4_0.gguf— Q4_0 GGUF for llama.cppadapter_model.safetensors— LoRA adapter weightsmetrics.jsonl— Training metrics per iteration
- Created
- Mar 24, 2026
- Updated
- Mar 24, 2026