Clean validated MLC/WebLLM packaging of google/gemma-4-E2B-it in q4f161` for browser-local WebGPU and MLC-LLM runtimes. This repository is built from a local mlc-llm / TVM fork and reflects the cleaned baseline validated on 2026-04-13. — Public HF artifact now matches the validated clean baseline. — Bug 9b fix is included; prefillchunksize=16 workaround is no longer needed. — Debug instrumentation and experiment branches are removed from the active path. — Public HF smoke test passes from the HF URL, including the canonical France/Paris case. — Text path: validated — Quantization: q4f161 — Runtime target: webgpu — Model type: gemma4 — Conversation template: gemmainstruction — Prefill chunk size: 1024 — Debug instrumentation: removed — Known chunk16 workaround: not required — libs/gemma-4-E2B-it-q4f161-MLC-webgpu.wasm: validated WebGPU model library — mlc-chat-config.json: MLC runtime configuration — paramsshard.bin: quantized parameter shards — tensor-cache.json: tensor metadata cache — tokenizer.json, tokenizerco The…
Модальности:
Генерация текста
Задача: Генерация текста
Автор: welcoma
Теги: MLC-LLM, web-llm, webgpu, gemma4, quantized, browser
Лайков: 3 | Загрузок: 0
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
