Skip to content

docs: add Cosmos3 Reasoner Transformers notebook #241

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
OasisYang wants to merge 2 commits into
base: main
Choose a base branch
from
+460 −1
Open

docs: add Cosmos3 Reasoner Transformers notebook #241

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e5b686e
docs: add Cosmos3 Reasoner Transformers notebook
Jun 24, 2026
bb5fbe9
docs: pin torchvision to 0.25.0 in Transformers notebook and README
Jun 25, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion cookbooks/cosmos3/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,7 +180,7 @@ uv pip install --torch-backend=auto \
pillow \
"safetensors>=0.8.0" \
torch \
torchvision \
"torchvision==0.25.0" \
"transformers>=5.11.0"
```

Expand Down
11 changes: 11 additions & 0 deletions cookbooks/cosmos3/reasoner/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -272,3 +272,14 @@ To run **Cosmos3-Super**, change `model_id` to `nvidia/Cosmos3-Super`.
`device_map="auto"` can shard the model across multiple GPUs when Accelerate is
installed. Use [vLLM](#run-with-vllm) or [NIM](#run-with-nim) when you need an
OpenAI-compatible server instead of local Python inference.

### Notebook walkthrough

[`run_with_transformers.ipynb`](./run_with_transformers.ipynb) is the Python-first
counterpart to the server notebooks: instead of launching a server, it installs an
isolated venv, registers a `Cosmos3 Transformers (Python 3.13)` Jupyter kernel,
and loads `Cosmos3OmniForConditionalGeneration` in process. A small
`run_reasoner` helper wraps `apply_chat_template` + `generate`, and the notebook
then runs the image and video examples shown above. To scale from **Nano** to
**Super**, change only `model_id` in the load cell and re-run; `device_map="auto"`
shards Super across multiple GPUs.
Loading