clue-ai/ChatYuan

Issues

• AttributeError: 'T5Model' object has no attribute 'chat'

  #64 opened a year ago by xihaofei
  0

• app_gradio.py 启动后，运行错误，http 响应422 Unprocessable Entity

  #60 opened a year ago by yangzilong1986
  3

• 本模型支持repetition_penalty吗？

  #63 opened a year ago by yitan800
  0

• 本模型如何应用DeepSparse, VLLM?

  #62 opened a year ago by yitan800
  0

• 如何转成onnx模型呢？

  #61 opened a year ago by xman1991
  0

• 请问下支持的输入文本最大长度和输出文本最大长度是多少呢？

  #57 opened a year ago by songyingxin
  1

• '<class 'transformers.models.t5.configuration_t5.T5Config'>' is already used by a Transformers model

  #59 opened 2 years ago by liuxindtc
  5

• 微调时无法使用FP16损失为nan

  #58 opened 2 years ago by WangYuhang123
  0

• 拒答能力如何增强的？

  #42 opened 2 years ago by murray-z
  2

• 启动时DLL错误

  #56 opened 2 years ago by qichuang119
  0

• 这个参数量多大呢？

  #54 opened 2 years ago by sjm1992st
  0

• 基本常识都没有

  #53 opened 2 years ago by g-wellsa
  0

• add the repo to https://github.com/nichtdax/awesome-totally-open-chatgpt

  #25 opened 2 years ago by alreadydone
  2

• int4版本

  #46 opened 2 years ago by imshadow
  1

• INT4 版本模型

  #30 opened 2 years ago by JunchengYao
  2

• 离线怎么部署呀,Repo id must be in the form 'repo_name' or 'namespace/repo_name': './ClueAI/ChatYuan-large-v2'

  #48 opened 2 years ago by cghk002
  5

• fine-tuning为什么只回答训练数据里面的答案？即使问题不在训练数据内

  #52 opened 2 years ago by RosieYC
  1

• 是否支持stream_chat

  #51 opened 2 years ago by yuanjie-ai
  1

• 可以支持下model.stream_chat不

  #50 opened 2 years ago by yuanjie-ai
  0

• 可以基于你们的模型生成句子embedding吗

  #49 opened 2 years ago by yuanjie-ai
  1

• 分布式训练 是 数据并行 还是 模型并行？感觉要 模型并行 才能成为大模型，是吧？

  #32 opened 2 years ago by guotong1988
  1

• [finetune] 请问下如果从t5模型微调训练出ChatYuan-large-v1模型

  #44 opened 2 years ago by Tian14267
  3

• 怎样离线使用这个程序？

  #45 opened 2 years ago by a0ge0a
  3

• 关于distributed训练的问题

  #47 opened 2 years ago by Tian14267
  3

• 请问如何基于YUAN模型进行无监督预训练

  #18 opened 2 years ago by zhangzai666
  1

• url在哪里改，我服务器端部署webUI，后台显示是成功的，但是无法连接，后台也没有连接请求（我端口开了，防火墙关了）

  #41 opened 2 years ago by knigth95
  2

• prompt数据会开源吗？

  #34 opened 2 years ago by murray-z
  1

• 请问ChatYuan和Yuan的关系是什么？

  #40 opened 2 years ago by 2catycm
  3

• 按照示例运行报错

  #33 opened 2 years ago by zhihao-chen
  7

• 作者您好，请教问题：tokenizer词表大小和模型embedding层对应不上

  #39 opened 2 years ago by zhangzai666
  2

• 文件都已经下载好了，但还是说找不到文件

  #35 opened 2 years ago by ddzz0210
  2

• help：无法加载本地模型

  #38 opened 2 years ago by nuo-o
  1

• 训练数据如何无监督？

  #36 opened 2 years ago by szpnygo
  1

• 还需要调整

  #31 opened 2 years ago by toolgood
  1

• 在dsw安装魔塔报错

  #29 opened 2 years ago by lvjianxin
  3

• Context & Cot seems to need more prompt learning

  #27 opened 2 years ago by yhyu13
  3

• OMP: Error #15:

  #28 opened 2 years ago by lvjianxin
  0

• 升级v2版本后频繁遇到长时间无响应

  #26 opened 2 years ago by Tomorrowxxy
  2

• 如何基于YUAN模型进行无监督预训练？

  #19 opened 2 years ago by zhangzai666
  3

• 没有通过我的测试🤣

  #17 opened 2 years ago by thisred
  1

• 按照README上面的实例运行报错

  #15 opened 2 years ago by sxk000
  2

• prompt tuning数据开源吗？

  #16 opened 2 years ago by wantsjean
  1

• 怎么做增量训练

  #14 opened 2 years ago by SamaelChen
  1

• finetune后推理时部分问题的输出为None

  #13 opened 2 years ago by yaleimeng
  3

• fine-tune out of memory

  #10 opened 2 years ago by jiangix-paper
  5

• 代码效果略奇怪啊，finetune也没有效果

  #11 opened 2 years ago by cspanda8989
  3

• 该模型能用于限定域的问答任务吗？怎么加入自己的语料？

  #12 opened 2 years ago by caisuxian
  1

• 这个repo的issues真的很好看

  #9 opened 2 years ago by ZeyuTeng96
  1

• feedback

  #7 opened 2 years ago by mzhaoshuai
  3

• 这图真假？

  #8 opened 2 years ago by blazer233
  1