OCPP-PulseEnergy/pulseenergy-ocpp-llm

pulseenergy-ocpp-llm

A fine-tuned diagnostics model for OCPP (Open Charge Point Protocol) EV charging networks, built by Pulse Energy. It is trained to interpret OCPP message logs, surface likely root causes for charger faults, and explain protocol-level behaviour in plain language.

Model details

• —Developed by: Pulse Energy Technologies Pvt. Ltd.
• —Base model: Qwen2.5-7B
• —Language: English
• —License: MIT

Intended use

Designed for charge point operators (CPOs) and support teams to:

• —Diagnose charger faults from OCPP message traces (BootNotification, StatusNotification, MeterValues, StartTransaction/StopTransaction, etc.)
• —Map OCPP error codes and status transitions to probable causes
• —Explain OCPP 1.6 / 2.0.1 protocol behaviour and message semantics
• —Assist first-line support triage before escalation

Limitations and recommendations

• —Coverage is strongest for common OCPP 1.6 fault patterns; rarer or vendor-specific extensions may be less reliable.
• —The model can produce plausible but incorrect root-cause attributions; keep a human in the loop for any operational action.
• —Recommended decoding: low temperature (≈0.2–0.4) for deterministic diagnostics.

Citation

@misc{pulseenergy_ocpp_llm,
  title  = {pulseenergy-ocpp-llm: An OCPP Diagnostics LLM},
  author = {Pulse Energy Technologies},
  year   = {2026},
  howpublished = {\url{https://huggingface.co/OCPP-PulseEnergy/pulseenergy-ocpp-llm}}
}