Downloads · 30 days
0
Siyuc/qwen35-4b-synthetic-qa-grpo-step40
qwen35-4b-synthetic-qa-grpo-step40 is a reinforcement learning model from Siyuc. 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 megatron-core. The card lists the license as other.
This private repository stores a resumable Megatron/Slime distributed training checkpoint.
Downloads · 30 days
0
Access
Public
Updated Aug 27, 2026
Repo size
71 GB
Likes
0
Public
Click a slice to open those files.
.distcp71 GB · 100%
From the Hugging Face model README
This private repository stores a resumable Megatron/Slime distributed training checkpoint.
torch_distThe repository includes model/optimizer/RNG checkpoint shards, the checkpoint iteration marker, and the rollout dataset state needed to resume the original training run.
This is a training checkpoint, not a directly loadable Transformers model export.