" modelscope中，同样的代码 在notebook 之前没有问题，现在报错，怎么解决？ 2024-06-13 17:06:18.863321: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0.
2024-06-13 17:06:19.498306: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-06-13 17:06:20.814508: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
RuntimeError: Unsloth: /mnt/workspace/.cache/modelscope/hub/llm-research/meta-llama-3-8b-instruct is not a full model or a PEFT model."
写回答
ModelScope旨在打造下一代开源的模型即服务共享平台，为泛AI开发者提供灵活、易用、低成本的一站式模型服务产品，让模型应用更简单！欢迎加入技术交流群：微信公众号：魔搭ModelScope社区，钉钉群号：44837352
