openeuler/llmopenEuler LLM container image includes
SDK: SDK for different computing platformAI Framework: AI frameworks, such as PyTorch, Tensorflow, etc.Tools: Tools to support the LLMLLM: LLMs, such as llama-2, chatglm, etc.All LLM container images are based on openEuler from openeuler/openeuler. The supported tags are:
chatglm2_6b-pytorch2.1.0.a1-cann7.0.RC1.alpha002-oe2203sp2fastchat-pytorch2.1.0.a1-cann7.0.RC1.alpha002-oe2203sp2To start a container from openEuler LLM image, users should first be ready for the corresponding hardware platform, such as Nvidia, AMD, or Ascend, etc.
For example, users can start the chatglm2-6b container with image of chatglm2_6b-pytorch2.1.0-cann7.0.0.alpha001-oe2203sp2 on Ascend platform by the following command:
docker run --device /dev/davinci0 --device /dev/davinci_manager --device /dev/devmm_svm --device /dev/hisi_hdc -v /usr/local/dcmi:/usr/local/dcmi -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi -v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ -ti openeuler/cann:chatglm2_6b-pytorch2.1.0.a1-cann7.0.RC1.alpha002-oe2203sp2 bash
manifest unknown 错误
TLS 证书验证失败
DNS 解析超时
410 错误:版本过低
402 错误:流量耗尽
身份认证失败错误
429 限流错误
凭证保存错误
来自真实用户的反馈,见证轩辕镜像的优质服务