stackformers
Composable PyTorch transformers for vision, spatial, and sequence research
What XERJ indexed
Snapshot
The whole repository at commit a09f3a0d18 (2026-10-16). main is 19 commits ahead.
Selected work
“Expand transformer branches into named steps”. 5 files, 275 lines in stackformers, the project root.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-27. Same terms as the repository. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution
attentioncomputer-visiondeep-learningpoint-cloudpytorchresearchtransformers
Example questions
- How does stackformers implement attention?
- Where does stackformers handle “Expand transformer branches into named steps”?
- What does stackformers do in stackformers?
Inside the indexed corpus
- Languages by size: Python 99.9%, Just 0.1%.
- On GitHub since 2026-05-12, last push 2026-10-28, 132 commits on main.
- The pin is 19 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for Red-Eyed/stackformers on 2026-10-29, and the LICENSE file at commit a09f3a0d18 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Vadym Stupakov (@Red-Eyed) has 1 selected repository on the hub.
Using XERJ with stackformers
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- Best MCP servers for local code search in 2026, compared
- Best grep alternative for AI coding agents (2026)
- Ask questions about a GitHub repo without cloning it
The prompt
Paste it into your AI agent. It clones Red-Eyed/stackformers at the pinned commit and indexes it on your machine.
Search the GitHub repository Red-Eyed/stackformers with XERJ (https://hub.xerj.org/corpus/red-eyed--stackformers). Run these in a shell, in order, and check each result before the next: 1. xerj --help (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh 2. git clone https://github.com/Red-Eyed/stackformers stackformers && git -C stackformers checkout a09f3a0d188bfa9d531ea25ca7de296f6bf525f2 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./stackformers --url http://127.0.0.1:9200 --prefix stackformers --progress plain 5. xerj autoindex map --url http://127.0.0.1:9200 Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt Licence: MIT. Keep the copyright notice and credit the authors.
Related
Vadym StupakovAI, prompts and agents corporaflexragcamelfastragyanivbahalul/RiddickDeepLearnPhysics/spinekornia/kornia
Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.