PKU-YuanGroup/ChatLaw

Issues

• 执行转llama-13b 为 llama-13b-hf 时，报LlamaConfig 找不到问题

  #60 opened a year ago by nuaabuaa07
  1

• 我建了一个微信交流群，欢迎相互交流！

  #75 opened a year ago by liushifu12138
  5

• Where is a Demo for the ChatLaw2-MoE model described in the Readme?

  #86 opened 2 months ago by MartialTerran
  0

• 您好，请问下载模型的验证码是什么？

  #83 opened 2 months ago by yichen2334
  0

• 关键词提取模型的训练数据

  #42 opened a year ago by ZMingHang
  2

• 不能登录啊

  #85 opened 6 months ago by misijiawen
  0

• Where i can find config.json

  #46 opened a year ago by binhthuong
  3

• The vocab size of the tokenizer 39410 is smaller than the vocab size of the base model 39424 This is not the intended use. Please check your model and tokenizer.

  #84 opened 6 months ago by wtmshanbao
  0

• 为啥执行结果是乱码？

  #79 opened 7 months ago by forbinarry
  1

• 关于论文中提及的reference module的疑问

  #78 opened 7 months ago by Jokerkakkoii
  0

• 请问数据集都是从哪里搜集的？

  #77 opened 8 months ago by Janet-Baker
  1

• ImportError: cannot import name 'LlamaForCausalLM' from 'transformers'

  #39 opened a year ago by hujb2000
  1

• 输入过长会导致回答很奇怪

  #76 opened 9 months ago by yuquanle
  0

• 内测申请

  #57 opened a year ago by HualeiZhuu
  2

• 请问评测数据是否开源

  #56 opened a year ago by zhangyu68
  1

• 训练数据的量级及配比问题

  #54 opened a year ago by zhangyu68
  1

• 13b的模型跑起来，需要多少显存资源

  #45 opened a year ago by Jonsun-N
  12

• 希望取得联系

  #74 opened a year ago by ANDY9411
  0

• 关于Algorithm1步骤7中的s

  #73 opened a year ago by amutong
  0

• 关键词向量和用户问题向量加权的权重是多少呢？

  #69 opened a year ago by liuweie
  1

• RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0!

  #64 opened a year ago by nuaabuaa07
  6

• 能大概分享一下keyWord模型的训练思路吗

  #47 opened a year ago by controZheng
  2

• chatlaw部署在本地之后能够实现对法律问题中的关系进行提取？

  #71 opened a year ago by Forfity-l
  0

• 合伙法律法规

  #70 opened a year ago by arvinlu888
  0

• 关于模型生成错误的法条情况的反映（附个人的解决方案.个人愚见）

  #63 opened a year ago by QAyong
  5

• 请教下text2vec模型文本对数据的生成方式

  #68 opened a year ago by AugustLHHHHHH
  0

• 33B的模型跑起来需要多大的显存？

  #67 opened a year ago by weironggege
  0

• 输入长度

  #66 opened a year ago by woshuia
  0

• peft model inference so slow!!

  #65 opened a year ago by KLGR123
  0

• 模型合并好了，跑示例代码报错了

  #41 opened a year ago by xjlv1113
  1

• 在线体验地址不能用了，是有什么限制吗？

  #62 opened a year ago by liuyx-baller
  0

• 33B的模型如何加载呢？

  #61 opened a year ago by WangxuP
  1

• 想问专业版里，根据用户query反问问题这部分功能的数据是怎么构造呢？

  #59 opened a year ago by Pattaro
  0

• 合并以后跑出来的是unk

  #37 opened a year ago by ScottishFold007
  1

• 请问有人能复现出来不错的结果吗

  #58 opened a year ago by zhangyu68
  0

• 希望取得联系

  #55 opened a year ago by JimmyMa99
  0

• Web UI

  #31 opened a year ago by rattlesnakey
  3

• 微调训练机器配置和时长

  #53 opened a year ago by jcyao
  0

• LLaMa2 权重发布了，有没有相应的合并？

  #52 opened a year ago by ucas010
  0

• 论文中input vector和keyword vector计算Vi的时候， α是怎么初始化的

  #51 opened a year ago by Tungsong
  0

• chatlaw模型权重在哪下载

  #50 opened a year ago by hfyer
  0

• “we fine-tuned an LLM to extract the keywords from user queries.”

  #38 opened a year ago by iGangao
  3

• self-suggestion部分是如何构建数据的

  #30 opened a year ago by felixstander
  4

• Is retrieval used for the other models as well?

  #44 opened a year ago by EnnioEvo
  0

• 关于训练数据demo中meta_instruction的问题

  #43 opened a year ago by s1ghhh
  0

• 官方交流群 微信二维码提示：超200人，无法加群

  #29 opened a year ago by leochenliu
  10

• 预训练阶段数据量级

  #40 opened a year ago by nuoma
  0

• 怎么保留基座模型原有的问答能力

  #35 opened a year ago by suckseed5
  0

• 为什么Huggingface仓库没有config.json文件呢，模型合并了也无法运行啊

  #34 opened a year ago by Danny-C-Auditore
  0

• 模型不运作

  #32 opened a year ago by shaozheng0503
  0