Text Generation
Transformers
PyTorch
Chinese
bloom
text-generation-inference
Inference Endpoints

为何不能使用inference API调用?

#1
by tianhaotiger - opened

Could not load model xyz-nlp/XuanYuan2.0 with any of the following classes: (<class 'transformers.models.bloom.modeling_bloom.BloomForCausalLM'>,).

This comment has been hidden

transformers版本4.29.1

网页右边的compute也用不了。Could not load model xyz-nlp/XuanYuan2.0 with any of the following classes: (<class 'transformers.models.bloom.modeling_bloom.BloomForCausalLM'>,).

每次对话max_tokens是多少? 最新的数据到多会?有实时金融行情吗?

This comment has been hidden

Could not load model xyz-nlp/XuanYuan2.0 with any of the following classes: (<class 'transformers.models.bloom.modeling_bloom.BloomForCausalLM'>,).

已支持,但是线上CPU需要运行很长时间,且可能会有以下提示:The model xyz-nlp/XuanYuan2.0 is too large to be loaded automatically (352GB > 10GB). For commercial use please use PRO spaces (https://huggingface.co/spaces) or Inference Endpoints (https://huggingface.co/inference-endpoints).

xyz-nlp changed discussion status to closed

尝试了一个寂寞

尝试了一个寂寞

是遇到什么问题了吗?如果有问题请及时反馈

怎么获取api阿

怎么获取api阿

请您将模型下载后使用,目前没有可以调用的api

Sign up or log in to comment