Views
No views yet
chat_template to tokenizer_config.jsonchat_template field. Without it, the serving engine cannot format role-based messages (system, user, assistant) with the special tokens the model expects (<|im_start|>, <|im_end|>). Raw text is sent instead, producing garbled output because the model was trained on the ChatML format.chat_template from the official Qwen/Qwen3-8B repository. This template handles system/user/assistant role formatting, tool calls (<tool_call>/</tool_call>), thinking mode (<think>/</think>), and the enable_thinking toggle.base_model in README metadatameta-llama/Meta-Llama-3.1-8B as the base model. The actual architecture is Qwen3: config.json specifies Qwen3ForCausalLM with 36 layers, 4096 hidden_size, 32 attention heads, 8 KV heads, and vocab_size 151936. The tokenizer is Qwen2Tokenizer. These all match Qwen/Qwen3-8B, not Meta-Llama.