Instructions to use prasadvittaldev/dogmatix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prasadvittaldev/dogmatix with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="prasadvittaldev/dogmatix")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("prasadvittaldev/dogmatix", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use prasadvittaldev/dogmatix with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "prasadvittaldev/dogmatix" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "prasadvittaldev/dogmatix", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/prasadvittaldev/dogmatix
- SGLang
How to use prasadvittaldev/dogmatix with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "prasadvittaldev/dogmatix" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "prasadvittaldev/dogmatix", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "prasadvittaldev/dogmatix" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "prasadvittaldev/dogmatix", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use prasadvittaldev/dogmatix with Docker Model Runner:
docker model run hf.co/prasadvittaldev/dogmatix
dogmatix β π§ Coming Soon
dogmatix is a small, local Python coding agent β a fine-tune of Google's Gemma-4-E2B-it (β2.3B effective parameters) that runs on a single consumer GPU. It has strong general Python skills and is specialized as a web-application agent: it reads files, edits code, runs the tests, and keeps iterating until they pass.
An initiative and project by Prasad Vittaldev. Weights are being trained now β this page will be updated with the released model shortly.
What it does
- General Python + web specialization: FastAPI, Flask, Django, ORMs (SQLAlchemy / PostgreSQL, Django ORM), and HTML / Jinja templates.
- Agentic by design: operates in a real coding-agent tool loop (
read_file/write_file/list_files/run_tests), doing multi-step read β edit β test β fix. - Local & private: runs in 4-bit on a 16 GB GPU β no data leaves your machine.
- Harness-ready: serves behind an Anthropic Messages API or OpenAI Chat Completions endpoint, so it drops into common coding-agent harnesses.
How it's built
A QLoRA fine-tune of gemma-4-E2B-it, distilled from executed, test-verified agent trajectories β a stronger teacher model solves sandboxed web-app tasks inside the real tool loop, and only trajectories whose hidden tests pass become training data. Broad Python knowledge comes from curated open Python instruction datasets. The result learns genuine tool use and self-verification, not imagined tool outputs.
π Coming soon (by Prasad Vittaldev)
- β
The released model weights β load directly with
transformers. - π Benchmarks on a held-out web-app coding suite (early runs show a large jump in executed pass@1 and in multi-step tool use vs. the base model).
- π§© End-to-end web-app tasks β models + routes + templates + Postgres, together.
- πͺ Long-task support via task decomposition + context compaction.
- π§ͺ Recovery-focused training (learning to fix its own failing tests) for higher reliability.
- π¦ Ready-to-serve setup for Claude Code / Pi-style harnesses.
License
Apache 2.0, consistent with the base model google/gemma-4-E2B-it.
Contact
dogmatix is an initiative and project by Prasad Vittaldev. For questions or collaboration: prasadvittaldev@gmail.com
