galavoxx/llama-3.2-3b-phaedo-ext-comprehensive335-q4f16-MLC

Llama-3.2-3B-Phaedo-Ext-Comprehensive335-q4f16-MLC

Built with Llama

A LoRA fine-tune of Llama 3.2 3B Instruct that reads a conversation and emits structured signals about how the person on one side of it prefers to be communicated with — the extraction stage of Phaedo, a cognitive-fingerprint system that runs entirely on the user's own devices.

What it does

Given a conversation transcript, it emits signals across eight layers (communication style, working style, domain, and so on) in a fixed catalogue. It is not a chat model and it is not useful for general instruction-following — it was trained on one narrow task and is scored on that task alone.

Intended use and limits

• —Intended: local, on-device extraction of communication preferences from the user's own conversations, with the output staying on their device.
• —Not intended: inference about people who have not consented, demographic or protected- attribute inference, or any use the Llama 3.2 Acceptable Use Policy prohibits.
• —Known limit: it emits catalogue signals only. A trait outside the catalogue is not represented, and absence of a signal is not evidence of its opposite.

Training

Inherited from the source model: LoRA SFT over unsloth/Llama-3.2-3B-Instruct on a synthetic corpus of 335 labelled conversations. This repository adds quantization only — no further training.

This is the build that actually runs

q4f161 MLC weights, ~1.81 GB, for `@mlc-ai/web-llm` **0.2.84** (model lib `v0284/base/…wasm`). The `mlc-chat-config.json` and tokenizer are reused verbatim from `mlc-ai/Llama-3.2-3B-Instruct-q4f161-MLC so the output loads against that runtime — which is a compatibility constraint, not a convenience. The unquantized source model is [galavoxx/llama-3.2-3b-phaedo-ext-comprehensive335`](https://huggingface.co/galavoxx/llama-3.2-3b-phaedo-ext-comprehensive335).

It downloads only when a Phaedo user turns the on-device reader on. It is off by default.

License

Llama 3.2 Community License — not an OSI open-source license. The full agreement is in LICENSE.txt in this repository; the required attribution is in NOTICE. Use of this model is subject to the Llama 3.2 Acceptable Use Policy.

Phaedo's own code is Apache-2.0. This model is not, and the distinction matters: a Phaedo deployment that includes this model carries the Llama license terms with it.