Instructions to use Wellz1000/hermes-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- HERMES
How to use Wellz1000/hermes-2 with HERMES:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download agent/monitoring/__init__.py from Wellz1000/hermes-2: direct link, hf CLI and curl.
- Browser
- Download file 985 Bytes
-
https://huggingface.co/Wellz1000/hermes-2/resolve/main/agent/monitoring/__init__.py
- Command line
-
hf download hf://Wellz1000/hermes-2/agent/monitoring/__init__.py
-
curl -L -o __init__.py https://huggingface.co/Wellz1000/hermes-2/resolve/main/agent/monitoring/__init__.py
985 Bytes
| """Hermes gateway monitoring. | |
| Service health monitoring plus redacted operational diagnostics for the | |
| gateway daemon, exported over OTLP to an operator-configured endpoint. | |
| ``emitter`` is the in-process event bus: producers (gateway status hooks, | |
| the diagnostic log handler) hand typed events to a fire-and-forget queue, | |
| and subscribers (the OTLP streamers) consume them off the hot path. The | |
| emitter never blocks or raises into gateway code (the hot-path invariant), | |
| and nothing is persisted locally — monitoring is an egress path, not a store. | |
| Deliberately out of scope here: run/model/tool trajectory capture, usage | |
| analytics, and any content-bearing signal. Those planes are served by the | |
| NeMo Relay integration and its Hermes-owned subscribers. | |
| """ | |
| from __future__ import annotations | |
| from . import emitter, events | |
| emit = emitter.emit | |
| get_emitter = emitter.get_emitter | |
| __all__ = [ | |
| "emitter", | |
| "events", | |
| "emit", | |
| "get_emitter", | |
| ] | |