UDGAM LABS · Tool-calling model, GGUF files · 384M parameters This repo holds the GGUF files of Udgam-384M-Chat for llama.cpp, Ollama and LM Studio: A 384M-parameter English model for on-device tool calling, trained from scratch by Udgam Labs. It is a decoder-only transformer compatible with the Gemma 4 architecture (Gemma4ForCausalLM), so it runs unmodified in Ollama, LM Studio, llama.cpp, MLX and transformers. Context: 4,096 tokens. The 4-bit GGUF is 238 MB. Built for four jobs inside an app: 1. App actions: turn a request into a function call. «wake me at 6:45, label it gym» → setalarm{time:»06:45″, label:»gym»}. 2. Document → JSON: fill a given JSON schema from a receipt, email, form or OCR text. 3. Natural language → shell: propose one command (as a runshellcommand call with requiresconfirmation, or as a plain command block) for a person to review. 4. Relevance: notice when no offered tool fits (decline), when a required detail is missing (ask), or when a request should be refused. What it is not: a knowledgeable general assistant (at 384M parameters it makes factual mistakes), or a safety-hardened open chatbot. Use it where your app decides which tools exist and confirms…
Модальности:
Генерация текста
Области применения:
Диалог / чат Вызов функций (Tool use)
Языки программирования:
Bash/Shell
Задача: Генерация текста
Автор: udgamlabs
Теги: gguf, udgamlabs, gemma4, tool-calling, function-calling, on-device, json-extraction, shell
Лайков: 3 | Загрузок: 671
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.