Gemma3-1B-LOMO-q4f16_1-MLC

MLC-LLM formatted weights for on-device inference.

• Conv template: gemma3_instruction (runtime prompt formatting should match training)
• Files
  • mlc-chat-config.json
  • params_shard_*.bin
  • tensor-cache.json
  • tokenizer files (tokenizer.json + tokenizer.model or vocab.json + merges.txt)

Quick test (CLI)

mlc_llm chat HF://raining-codes/Gemma3-1B-LOMO-q4f16_1-MLC   --temperature 0.7 --top-p 0.9 --repeat-penalty 1.08 --max-gen-len 512