支持直接读取的模型 THUDM/glm-4-9b-chat meta-llama/Meta-Llama-3-8B-Instruct meta-llama/Meta-Llama-3-70B-Instruct Qwen/Qwen2-0.5B-Instruct Qwen/Qwen2-1.5B-Instruct Qwen/Qwen2-7B-Instruct Qwen/Qwen2-72B-Instruct