Qihoo360/360zhinao

Issues

• 运行huggingface上reranking的示例报错ModuleNotFoundError: No module named 'transformers_modules.360Zhinao-1

  #21 opened 4 months ago by CarreLiu
  0

• 运行huggingface上reranking的示例报错ModuleNotFoundError: No module named 'transformers_modules.360Zhinao-1

  #20 opened 5 months ago by sssuperrrr
  1

• 按照这个调用方法执行reranking模型 报错没有这个model id

  #19 opened 5 months ago by standing88
  0

• when run rerank model demo error...

  #18 opened 6 months ago by hegang1-tal
  0

• RAG应用中如何使用qihoo360/360Zhinao-1.8B-Reranking，可以给个例子吗？

  #17 opened 6 months ago by shizidushu
  3

• vllm bug

  #15 opened 7 months ago by zky001
  0

• Token indices sequence length is longer than the specified maximum sequence length for this model (8473 > 4096). Running this sequence through the model will result in indexing errors

  #14 opened 7 months ago by 81286300
  0

• { "msg": "name 'message' is not defined", "status_code": 500 }

  #13 opened 8 months ago by linjianwei888
  0

• 运行微调代码时提示#error "PYTHON < 3.6 IS UNSUPPORTED. pybind11 v2.9 was the last to support Python 2 and 3.5.错误

  #10 opened 8 months ago by alfiy
  1

• 多模态大模型访问方式

  #12 opened 8 months ago by 77h2l
  0

• 运行微调时报错“torch.cuda.OutOfMemoryError: CUDA out of memory. ”

  #11 opened 8 months ago by alfiy
  1

• 项目运行360Zhinao-7B-Chat-32K 'NoneType' object is not callable

  #8 opened 8 months ago by choshiho
  10

• Not compatible with vllm 4.0

  #3 opened 8 months ago by zollty
  2

• 是否会支持llama.cpp模型转换至gguf？

  #2 opened 8 months ago by flyfox666
  1

• 项目无法运行推理360Zhinao-7B-Chat-360K-Int4和360Zhinao-7B-Chat-32K-Int4两个量化版

  #7 opened 8 months ago by qingfeng2018
  2

• Failed building wheel for flash-attn

  #9 opened 8 months ago by jsoncode
  1

• BFloat16 is not supported on MPS

  #6 opened 8 months ago by coldwater2000
  0

• 问问题的时候出现错误，报错

  #5 opened 8 months ago by flyfox666
  1

• 关于模型大小及需要gpu内存大小的问题

  #4 opened 8 months ago by p7759809
  0

• 是否提供磁力

  #1 opened 8 months ago by hggq
  2