Downloads · 30 days
36
20% of all-time downloads
z369217411/Qwen3-30B-A3B-GRPO-W4A4-NoOverlong-Step800
Qwen3-30B-A3B-GRPO-W4A4-NoOverlong-Step800 is a reinforcement learning model from z369217411. 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.
This is the standalone Hugging Face export of the final policy checkpoint from the following NeMo-RL training run:
Downloads · 30 days
36
20% of all-time downloads
All-time downloads
176
Public
Parameters
30.5B
61.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors61.1 GB · 100%
From the Hugging Face model README
This is the standalone Hugging Face export of the final policy checkpoint from the following NeMo-RL training run:
grpo-qwen3-30ba3b-base-8n4g-dapo512-20k-nvfp4-pertoken-r2-20260806-0of3-tokenmean-allmlp-nooverlong-dequant-te3049-v1
Qwen/Qwen3-30B-A3B-Base0.44140625The NeMo-RL Megatron distributed checkpoint was converted with Megatron Bridge to a standard Transformers checkpoint. The exported weights are stored as 16 BF16 safetensors shards. Optimizer and dataloader state are intentionally not included; this repository is intended for inference, evaluation, or subsequent fine-tuning rather than exact optimizer-state training resumption.
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "shawnzzzzz/Qwen3-30B-A3B-GRPO-W4A4-NoOverlong-Step800"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype="auto",
device_map="auto",
)