THUDM/ChatGLM2-6B

Issues

• [BUG/Help] <title>ptuning微调后想要在此基础上进一步微调

  #635 opened 4 months ago by fan-xh
  0

• [BUG/Help] readme中清华云盘的模型文件版本不对，跑出来是乱码，需使用huggingface.co模型，麻烦更新

  #640 opened a year ago by CN-zhouyk
  2

• [BUG/Help] <pytorch_model.bin don't exists>

  #660 opened a year ago by sc-carson
  4

• [BUG/Help] 用vllm 起INT4量化版本的模型报错 类型不匹配 self_attention.dense.weight int4 shape [4096,2048] mismatch fp16 shape [4096, 4096]

  #680 opened 7 months ago by yjjiang11
  0

• [BUG/Help] <title>运行api.py报错

  #679 opened 7 months ago by cqray1990
  0

• [BUG/Help] <title>python api.py 后，点击链接 报错405 Method Not Allowed

  #678 opened 7 months ago by cqray1990
  0

• [BUG/Help] cannot import name '_sentencepiece' from partially initialized module 'sentencepiece'

  #662 opened a year ago by mericalandintent
  5

• [BUG/Help] ModuleNotFoundError: No module named 'transformers.models.mpt'

  #677 opened 7 months ago by EinKung
  1

• [Help] 我在把项目fork下来之后，替换为我自己的接口，用axios不是fetch，我可以确定的是接口是正常的流式返回，但是在本地跑的时候，调用这个接口会显示一次性返回，不是流式输出，我看了头信息都是没有问题的，但是部署在服务器中是没有问题的，是因为什么呢，要怎样解决呢，希望得到作者或者同行的帮助，谢谢

  #676 opened 7 months ago by wisdomlsh
  0

• [BUG/Help] <title>peft , deepspeed 下 p-tuning , AttributeError: 'NoneType' object has no attribute 'shape'

  #675 opened 9 months ago by xxhh1212
  0

• [Help] <title>关于微调ptuning不能达到训练集的效果，且不破坏原有结构实验

  #674 opened 9 months ago by Bingoyww
  0

• [BUG/Help] <title>python3.7 cli_demo.py 报错cannot set version_counter for inference tensor

  #673 opened 9 months ago by mxldjt
  0

• 运行python cli_demo.py报错

  #671 opened 9 months ago by mxldjt
  0

• [BUG/Help]UnstructuredFileLoade 读取 txt 文件 报错： zipfile.BadZipFile: File is not a zip file

  #670 opened 9 months ago by PedroNeal
  0

• [BUG/Help] <title>最后运行的时候出现这个问题，不知道怎么解决

  #669 opened 9 months ago by Oraclty
  0

• [Help] 6b-int4 lora 微调使用 adam 优化器时梯度爆炸

  #652 opened 9 months ago by wizardforcel
  1

• Unable to load weights from pytorch checkpoint file for '/home/qianlab03/rjs/Langchain-Chatchat-0.2.7/chatglm2-6b/pytorch_model-00001-of-00007.bin

  #668 opened 10 months ago by iaoxuesheng
  0

• [BUG/Help] 为什么chatglma2量化后weight的size会改变<title>

  #667 opened 10 months ago by Paradise59
  0

• [BUG/Help] <title>按照官方给出的多轮问答数据集构建问答数据之后，运行脚本命令出现Traceback (most recent call last): File "/mnt/ChatGLM2-6B/ptuning/main.py", line 411, in <module> main() File "/mnt/ChatGLM2-6B/ptuning/main.py", line 229, in main train_dataset = train_dataset.map( File "/root/anaconda3/envs/GLM2/lib/python3.9/site-packages/datasets/arrow_dataset.py", line 592, in wrapper out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs) File "/root/anaconda3/envs/GLM2/lib/python3.9/site-packages/datasets/arrow_dataset.py", line 557, in wrapper out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs) File "/root/anaconda3/envs/GLM2/lib/python3.9/site-packages/datasets/arrow_dataset.py", line 3180, in map with Pool(len(kwargs_per_job)) as pool:

  #666 opened 10 months ago by nevesaynever1
  0

• 请问现在大家目前有微调的效果比较好的方案吗，目前微调效果一直不理想。

  #665 opened 10 months ago by nevesaynever1
  0

• [BUG/Help] <title>chatglm2首token时延增长随输入长度成倍快速增长

  #664 opened a year ago by woaipichuli
  0

• [友情链接] <Colossal-AI加速ChatGLM2>

  #663 opened a year ago by Yanjia0
  0

• [Help] chatGLM2-6B是否支持直接注入整篇文档进行微调，如果支持怎么处理

  #655 opened a year ago by wangfenglei-hehe
  1

• [BUG/Help] <win10微调 失败：ValueError: None is not in list>

  #646 opened a year ago by wangyingdong
  2

• 请问chatglm1、chatglm2、chatglm3训练了多少种语言呢？

  #659 opened a year ago by fxb392
  0

• [BUG/Help] <title>微调后为什么聊着聊着说我chatbot为空

  #658 opened a year ago by LeoQianQY
  1

• [BUG/Help] <title>如何通过API来调用ChatGLM？

  #657 opened a year ago by 20130216
  0

• [Help] <title>用lora微调遇到这个问题RuntimeError: Expected to mark a variable ready only once.

  #645 opened a year ago by wfllyzh
  1

• [Help] 请问如何能做到微调过程中不保存早期的checkpoint

  #654 opened a year ago by ybdesire
  3

• [Help]有没有人尝试过把优化器改成SGD来减少显存占用的

  #633 opened a year ago by 31-ryougishiki
  1

• [BUG/Help] <title> ptuning的时候可以自定义loss吗？

  #656 opened a year ago by hhy150
  0

• 当我的transformers是4.36.2时，chatglm2不能正常加载

  #651 opened a year ago by Congcong-Song
  2

• [BUG/Help] <title>训练数据时显示ValueError: None is not in list，尝试过自己的json文件和AdvertiseGen提供的json文件

  #653 opened a year ago by Siqi-c
  0

• [BUG/Help] 求问 在做基于ChatGLM2-6B的Ptuning v2的微调任务时 损失/目标函数的公式是什么样子的

  #642 opened a year ago by Magicsmx
  1

• [BUG/Help] Nonetype bug for build_stream_inputs

  #650 opened a year ago by Dinghow
  1

• how to transfer chatglm2-6b int4 model to npu device

  #649 opened a year ago by woaipichuli
  0

• [Help] 请问ChatGLM2-6B 目前是否通过**相关部门的安全审查

  #648 opened a year ago by fengbrute
  0

• [BUG/Help] <title>6b-chat基模型输出bug

  #647 opened a year ago by HaomingX
  0

• [BUG/Help] <title>如何对微调前的模型进行推理

  #644 opened a year ago by DOVEEEEEEEEEEEEE
  0

• [BUG] `Both max_new_tokens and max_length seem to have been set` warning trigger

  #639 opened a year ago by callanwu
  1

• [BUG/Help] <title>实测C-Eval数据集中验证集所有subject的平均准确率与提供的结果有差异

  #638 opened a year ago by hongfengvvv
  0

• [Help] chatglm2是否有类似openai中stop的接口

  #637 opened a year ago by dbtzy
  0

• [BUG/Help] 请问一下本地部署了chatglm2，其回答总是会先复述一遍问题，这种情况应该如何解决

  #636 opened a year ago by iwannabeluchi
  0

• [BUG/Help] <title> 求可以下载chatglm2-6b-32k chatglm2-6b-base chatglm2-12b-base大模型文件的国内网盘

  #634 opened a year ago by 20130216
  1

• ChatGLM2用了FlashAttention，但是看源码没看到用在哪里[Feature] <title>

  #630 opened a year ago by WellWang-S
  0

• [BUG/Help] <title>没法git clone https://huggingface.co/THUDM/chatglm2-6b 试了很多次无果。抓狂中。。。

  #629 opened a year ago by 20130216
  1

• [Feature] 麻烦自己怎么离线量化呢？有方法吗

  #628 opened a year ago by lonngxiang
  0

• [Help] 模型在推理时是否存在记忆？

  #626 opened a year ago by CoderHiro
  0

• [Help] 请问api.py中的max_length参数具体指的是什么length

  #627 opened a year ago by zhengyangyong
  0

• UnicodeDecodeError: 'utf-8' codec can't decode byte 0xce in position 5811: invalid continuation byte

  #625 opened a year ago by 123eye
  0