OpenZero Gemma4 E2B Agentic is a small local GGUF research, coding and tool-workflow specialist. Choose the verified Q4KM, Q8_0 or F16 build; no PEFT archive or separate base model is required to run it. — Standalone model: yes — Separate adapter required: no — Separate base model required: no — Base architecture: google/gemma-4-E2B-it — Fine-tuning: 2,606 training examples; 137 held-out evaluation examples — Final held-out loss: 1.520900 — Held-out token accuracy: 0.657464 — GGUF conversion and CPU load test: passed for all three files with llama.cpp — Modality in this repository: text-only; no mmproj vision/audio projector is included Built for private local inference, prac Tool execution belongs to the surrounding runtime; validate outputs before acting on them. — Training adapter: QLoRA specialist run, 82/82 steps — Train loss: 2.261954 — Held-out evaluation loss: 1.520900 — Held-out token accuracy: 0.657464 — Q4KM — 3,416,119,872 bytes — SHA-256 9a7e717d13208526782c5fa5074bbcd7f445c6ac720e88d0e0e3ae6d87ebdeef — Q80 — 4,947,414,592 bytes — SHA-256 b612e7a6ffc2b9707f3b68e7e94fc8f8764e0975fefa4d1256717356f18af19f — F16…
Модальности:
Генерация текста
Области применения:
Диалог / чат Вызов функций (Tool use)
Задача: Генерация текста
Автор: shafire
Теги: llama.cpp, gguf, gemma, local-ai, agentic-ai, coding-assistant, research-assistant, tool-use
Лайков: 4 | Загрузок: 1,082
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
