Downloads · 30 days
5
11% of all-time downloads
weixu-zhang/qwen35-4b-grpo-phase3e-8lang3k-step1750
qwen35-4b-grpo-phase3e-8lang3k-step1750 is a machine learning model from weixu-zhang. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Merged actor checkpoint from the VisRL Phase 3e 8-language GRPO run.
Downloads · 30 days
5
11% of all-time downloads
All-time downloads
44
Public
Parameters
5.2B
10.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors10.4 GB · 100%
From the Hugging Face model README
Merged actor checkpoint from the VisRL Phase 3e 8-language GRPO run.
global_step_1750MAX_RESPONSE_LENGTH=768, BATCH_SIZE=3, N_SAMPLES=2, PPO_MINI_BATCH_SIZE=3