PYTHAI

/

mindXtrain

Like 0

Follow

pythai.net 2

bankml (github.com/cryptoAGI/bankml) is reached over HTTP and its CLI only;
nothing is vendored.

• operator/backends/bankml.py: @register_backend("bankml"), default
  MINDXTRAIN_BANKML_BASE_URL http://127.0.0.1:18093/v1; keeps the
  bankml_receipt (ChatResponse.receipt, last_receipt for streams); HTTP 400
  becomes BankmlRefusal(reason) and is never retried with altered params.
• operator: backend_kwargs() replaces the duplicated per-backend branches in
  app.py and coach/api.py; GET /bankml + /v1/models health probes;
  auto-detect tries bankml only after ollama and vllm; the governance panel
  env chain gains MINDXTRAIN_BANKML_BASE_URL last, only when set.
• deploy/bankml_push.py + serve --to bankml: merge -> Modelfile through
  bankml_sanitize (refuses ADAPTER, a foreign TEMPLATE, penalties, mirostat,
  typical_p, resource params; never drops them) -> bankml create; records
  the model sha256; refuses quantized configs and non-Llama archs; a bankml
  without create/convert (pre-0.3.5) is reported as bankml_too_old.
• eval/imprint_bankml.py + imprint-bankml: seeded, unpenalised greedy
  probes with a receipt per utterance, tagged /bankml-greedy and
  marked not comparable with the canonical 1.3-penalty gate.
• MEI engine literal += bankml; Gradio Serve room offers bankml; console
  omits penalty/mirostat options at the engine default; HF published
  Modelfile can omit repeat_penalty (default unchanged).
• docs/bankml.md, README, CLAUDE.md, NAV, cli, development, CHANGELOG,
  llm.txt. Tests: 56 new (821 passed, 3 skipped); ruff unchanged.

Co-Authored-By: Professor Codephreak codephreak@pythai.net

made with luv.pythai.net

Merged with one commit on top (437dccc): bankml 0.3.6.

• Penalties (repeat_penalty, repeat_last_n, presence_penalty, frequency_penalty) are taken in the Modelfile when bankml version is 0.3.6+ and refused, with the reason, before. serve --to bankml gains --bankml-system, --bankml-param KEY=VALUE and --bankml-stop. On gen39 the bare pin answers ",,,,"; the layered tag answers in words.
• The merged directory is converted through a link named after the tag, so llama.cpp's general.name is the tag's: gen39 converts to 6b64c748…, the GGUF mindX pins (through merged/ it was "Merged" and a different sha256). Verified against bankml 0.3.6 with this repo's gen39 weights.
• BankmlBackend sends sampling fields from options= / MINDXTRAIN_BANKML_OPTIONS, only when set.
• MINDXTRAIN_CHAT_MODEL / MINDXTRAIN_JUDGE_MODEL / MINDXTRAIN_CHAT_OPTIONS: the panel and the judges named llama3.2, which a bankml node does not serve.
• docs/install.md: deploying bankml 0.3.6 and this lane on the mindX VPS, step by step, with checks and a rollback.

852 passed, 3 skipped (842 + 10).

made with luv.pythai.net