Local, offline LLMs fine-tuned to be ComfyUI experts that drive the full comfyui-mcp tool surface — 178 tools (113 MCP server tools + 65 live-canvas panel tools) — in Gemma 4’s native tool-call format. These are the free, no-API-key backends for the comfyui-mcp Agent Panel: pick Ollama (local) in the panel and the agent edits your live graph, generates images/video/audio, manages models and custom nodes, and runs your workflows — entirely on your GPU. Pick by VRAM budget. Every rung is the same data, same recipe — only the base size changes. Each folder ships the GGUF quant(s), the LoRA adapter (r=32 — apply to the base or re-export any quant yourself), the trained chat template, and tokenizer/trainer configs. A stock model meets comfyui-mcp’s ~200-schema catalog cold and burns its context (and your patience) learning it. These models were trained on the tool suite itself: — Data: 1,055 server-verified tool-use trajectories (e4b/e2b; the earlier 12b rung trained on the initial 772) — synthesized TOUCAN-style against a live ComfyUI + comfyui-mcp server: task synthesis → real trajectory generation → server-verified filtering (every outcome checked against the actual server state,…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: artokun
Теги: gguf, comfyui, comfyui-mcp, tool-calling, agent, qlora, endpoints_compatible, conversational
Лайков: 3 | Загрузок: 2,059
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
