Downloads · 30 days
0
nemorl-gemma4-cu130-env
JWei05/nemorl-gemma4-cu130-env
nemorl-gemma4-cu130-env is a machine learning model from JWei05. 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.
Docker image tarball (docker save | zstd -6, 78.6GB uncompressed) with a fully built NVIDIA-NeMo/RL @ 5f89b3ae training environment:
Access
Public
Updated Jul 30, 2026
Repo size
29.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.zst29.5 GB · 100%
At a glance
- License
- other
- Access
- Public
- Created
- Jul 30, 2026
- Updated
- Jul 30, 2026
- SHA
- 2ad94105
Model card
From the Hugging Face model README
NeMo-RL gemma-4 cu130 environment image (H100/sm90)
Docker image tarball (docker save | zstd -6, 78.6GB uncompressed) with a fully built
NVIDIA-NeMo/RL @ 5f89b3ae training environment:
- CUDA 13.0 toolkit + cuda-compat + cuDNN 9 dev, cmake 4.0.3
- NeMo-RL checkout at
/workspace/rl-distill/third_party/nemo-rlwith its uv-locked cu130 driver venv (.venv: torch 2.11, TransformerEngine 2.14 compiled for sm90) - Prefetched Ray worker venvs at
/opt/ray_venvs(VllmGenerationWorker, DTensorPolicyWorkerV2) — no source builds at runtime
Contains only public/redistributable content (NVIDIA CUDA redistributables per the CUDA EULA, Apache-2.0 NeMo-RL, PyPI wheels). No model weights, no tokens, no private code.
huggingface-cli download JWei05/nemorl-gemma4-cu130-env rl-distill-nemorl-env-cu130-20260729.docker.tar.zst --local-dir .
zstd -d -c rl-distill-nemorl-env-cu130-20260729.docker.tar.zst | docker load
# then materialize your training repo around the baked checkout, e.g.:
# docker run ... rl-distill-nemorl-env:cu130-20260729 bash -c # 'cd /workspace/rl-distill && git init && git remote add origin <your-fork> && # git fetch --depth 1 origin main && git checkout -f FETCH_HEAD && <run>'
- License
- other
- Created
- Jul 30, 2026
- Updated
- Jul 30, 2026