WhitneyDesignLabs
/

wireclaw-agent-v1.3-lora

@@ -20,7 +20,9 @@ language:
 # WireClaw Agent v1.3 — LoRA adapter for Llama 3.1 8B Instruct
-**Built with Llama.** Second-generation fine-tune (v1.1 → v1.3) targeting **constitutional refusal robustness and article-citation discipline**. Trained on the Phase 4.1.x recovered production corpus + 180 targeted synthetic examples. Sibling release of [`wireclaw-agent-v1.1-lora`](https://huggingface.co/WhitneyDesignLabs/wireclaw-agent-v1.1-lora) — v1.1 remains the chip-production model; v1.3 is a discrete release with documented wins and bounded regressions.
 WireClaw is an agentic firmware that runs a local LLM (via the [WireClaw](https://github.com/M64GitHub/WireClaw) fork at [WhitneyDesignLabs/WireClaw](https://github.com/WhitneyDesignLabs/WireClaw)) and exposes tools the model can call to interact with the world. The agent receives a Telegram message, decides which tools to call, executes them, and produces a natural-language wrap-up — all under the Project Opengates Constitution.

 # WireClaw Agent v1.3 — LoRA adapter for Llama 3.1 8B Instruct
+> **⚠️ Superseded for chip production by [v1.3.1-lora](https://huggingface.co/WhitneyDesignLabs/wireclaw-agent-v1.3.1-lora)** (2026-05-20). v1.3 remains available as a discrete artifact and is preserved as an intermediate rollback tier on the Ollama host. v1.3.1 patches the harm-citation Article 3 / 12 specificity regression documented below and partially recovers the truth/uncertainty temp=0 hedge-engage behavior. See the v1.3.1 model card for the iteration trail and the new bounded regression (authorization category default temp) it introduces.
+**Built with Llama.** Second-generation fine-tune (v1.1 → v1.3) targeting **constitutional refusal robustness and article-citation discipline**. Trained on the Phase 4.1.x recovered production corpus + 180 targeted synthetic examples. Sibling release of [`v1.1-lora`](https://huggingface.co/WhitneyDesignLabs/wireclaw-agent-v1.1-lora) (prior chip-production) and [`v1.3.1-lora`](https://huggingface.co/WhitneyDesignLabs/wireclaw-agent-v1.3.1-lora) (current chip-production).
 WireClaw is an agentic firmware that runs a local LLM (via the [WireClaw](https://github.com/M64GitHub/WireClaw) fork at [WhitneyDesignLabs/WireClaw](https://github.com/WhitneyDesignLabs/WireClaw)) and exposes tools the model can call to interact with the world. The agent receives a Telegram message, decides which tools to call, executes them, and produces a natural-language wrap-up — all under the Project Opengates Constitution.