internlm2_5-7b-hf: demo_gsm8k_accuracy: 42.19 race-middle_accuracy: 91.78 race-high_accuracy: 90.02 internlm2_5-7b_hf: demo_gsm8k_accuracy: 42.19 race-middle_accuracy: 91.78 race-high_accuracy: 90.02 internlm2_5-7b-chat-lmdeploy: demo_gsm8k_accuracy: 84.38 race-middle_accuracy: 92.76 race-high_accuracy: 90.54 internlm3-8b-instruct-lmdeploy: demo_gsm8k_accuracy: 73.44 race-middle_accuracy: 93.38 race-high_accuracy: 90.34 internlm3-8b-instruct_hf-lmdeploy: demo_gsm8k_accuracy: 73.44 race-middle_accuracy: 93.38 race-high_accuracy: 90.34 internlm3-8b-instruct_hf-vllm: demo_gsm8k_accuracy: 78.12 race-middle_accuracy: 92.20 race-high_accuracy: 89.88 internlm2_5-7b-chat_hf: demo_gsm8k_accuracy: 87.50 race-middle_accuracy: 92.76 race-high_accuracy: 90.48 lmdeploy-api-test: gsm8k_accuracy: 68.75 race-middle_accuracy: 93.75 race-high_accuracy: 93.75