burmesegpt 0.1.0

Burmese-first Padauk GGUF runtime with OpenAI-compatible local API workflow

burmesegpt

burmesegpt is a Burmese-first local runtime for Padauk GGUF models with OpenAI-compatible /v1 API workflows. It helps you download verified model artifacts, serve them locally, and run quick CLI chat sessions.

Install

# Core package (download + info workflows)
pip install burmesegpt

# Include local server runtime for `serve` and local `run`
pip install "burmesegpt[server]"

download and info work with core install. serve and run (without --base-url) require burmesegpt[server].

Quickstart

Fast smoke test (no model download)

pip install "burmesegpt[server]"
burmesegpt serve --test-mode --port 8000

curl http://127.0.0.1:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"padauk-agent","messages":[{"role":"user","content":"hello"}]}'

Real model run

burmesegpt download --quant q8_0
burmesegpt serve --quant q8_0 --host 127.0.0.1 --port 8000

OpenAI-compatible Python example

from openai import OpenAI

client = OpenAI(base_url="http://127.0.0.1:8000/v1", api_key="sk-no-key-required")
response = client.chat.completions.create(
    model="padauk-agent",
    messages=[{"role": "user", "content": "Give me a short Burmese greeting."}],
)
print(response.choices[0].message.content)

CLI commands

• burmesegpt download — download and checksum-verify a quantized GGUF artifact.
• burmesegpt serve — start a local OpenAI-compatible API server.
• burmesegpt run — interactive chat (boots local server or uses --base-url).
• burmesegpt info — print package/model configuration as JSON.

Useful options:

• --quant: q4_k_m (default), q5_k_m, q8_0
• --repo-id, --revision, --cache-dir, --hf-token (or HF_TOKEN)

Docs

• Documentation index: docs/README.md
• HF to GGUF quantization guide: docs/guides/hf-to-gguf-quantization-guide.md
• PyPI release guide: docs/guides/pypi-release-guide.md

Release notes

• Published release history: https://pypi.org/project/burmesegpt/#history
• Current package version source: pyproject.toml ([project].version)