Downloads · 30 days
2
6% of all-time downloads
viscoder2-3b-grpo-phase3e-8lang3k-hfclean-legacypy-step5721
weixu-zhang/viscoder2-3b-grpo-phase3e-8lang3k-hfclean-legacypy-step5721
viscoder2-3b-grpo-phase3e-8lang3k-hfclean-legacypy-step5721 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.
Merged Hugging Face export of the final checkpoint from the phase3e full-parameter 3B run trained on the 8-language 3k/lang clean bundle.
All-time downloads
32
Public
Parameters
3.4B
6.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.8 GB · 100%
At a glance
- Model type
- qwen2
- Access
- Public
- Created
- May 16, 2026
- Updated
- May 16, 2026
- SHA
- 9802c6cf
Model card
From the Hugging Face model README
VisCoder2-3B GRPO Phase3e 8lang 3k/lang (step 5721)
Merged Hugging Face export of the final checkpoint from the phase3e full-parameter 3B run trained on the 8-language 3k/lang clean bundle.
- Base model:
TIGER-Lab/VisCoder2-3B - Training recipe: GRPO full-parameter finetuning
- Data:
- Python: legacy balanced
python_3000 - Other 7 languages: HF-cleaned 3k/lang bundle
- LaTeX: HF-clean 2877 + 123 legacy top-up
- Python: legacy balanced
- Languages: python, html, svg, vegalite, mermaid, lilypond, latex, asymptote
- Final checkpoint:
global_step_5721
Local source run:
- Output dir:
viscoder2_3b_grpo_phase3e_8lang3k_hfclean_legacypy_20260515_0942 - Merged actor:
global_step_5721/actor/hf_merged
This artifact is intended for evaluation / inference. Resume training should use the raw FSDP checkpoint rather than this merged export.
- Type
- qwen2
- Created
- May 16, 2026
- Updated
- May 16, 2026