datawhalechina/self-llm

Issues

• TypeError: transformers.generation.utils.GenerationMixin.generate() argument after ** must be a mapping, not Tensor

  #178 opened a day ago by LSK-1
  1

• GLM4接入langchain无法识别到RetrievalQA.from_chain_type下面的memory参数

  #179 opened a day ago by akira149
  1

• index-1.9b-chat 接入langchain报错

  #177 opened 2 days ago by jiangzhaokun
  1

• 05-Qwen2-7B-Instruct Lora 微调报错

  #176 opened 2 days ago by hgsw
  1

• qwen2 lora微调报错：RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

  #172 opened a day ago by ArlanCooper
  3

• 04-GLM-4-9B-Chat vLLM 部署调用显存溢出问题

  #162 opened 5 days ago by SongHY-13
  3

• Index-1.9B-Chat Lora 微调合并模型出现ValueError: Can't find 'adapter_config.json' at './output/Index-1.9B-Chat-lora/checkpoint-600'

  #175 opened 3 days ago by tangyipeng100
  1

• LlaMA3在英文或者中文上tokenizer是否需要加bos token？

  #140 opened 15 days ago by sugarandgugu
  3

• GLM-4-9b-chat web版运行时报属性messges不存在

  #173 opened 4 days ago by eagleLiu82
  2

• BUG：按照GLM-4示例不能启动API服务

  #174 opened 4 days ago by eternal-bug
  0

• 使用阿里云部署glm-4-9b api报gpu内存不足

  #169 opened 4 days ago by eagleLiu82
  4

• 如何获取一个大模型的stop_token_ids

  #170 opened 4 days ago by jdm4pku
  2

• 使用最新的peft进行lora微调，保存的checkpoint已经是合并的参数了，所以不需要分别加载再合并的操作了。

  #167 opened 4 days ago by whyjsw0719
  1

• deepseek-llm-7b-chat微调报错

  #171 opened 4 days ago by lzh123415
  1

• Index-1.9B-Chat webDemo部署报错问题

  #166 opened 5 days ago by gzhuuser
  3

• llama3 langchain

  #163 opened 5 days ago by Alexa2077
  1

• 有考虑添加多模态大模型的内容吗？

  #164 opened 5 days ago by sunhaha123
  1

• 深圳市原子同学？

  #165 opened 5 days ago by hunchunchao23
  2

• 使用 llama3 的 lora 微调报错：NotImplementedError: Cannot copy out of meta tensor; no data!

  #115 opened a month ago by chenmonster
  4

• 数据集如何构造？

  #161 opened 5 days ago by chopin1998
  0

• 微调出来会有不礼貌或攻击性的言语

  #108 opened a month ago by 1737686924
  4

• DeepSeek-7B-chat-Lora微调训练时报错

  #139 opened 16 days ago by 3Justice
  2

• 可以出一版验证集的process-func吗(Qwen、llama模型的数据集格式)？

  #151 opened 8 days ago by demouo
  1

• 2 warnings: MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization") / kernel version 4.18.0

  #152 opened 9 days ago by x6p2n9q8a4
  1

• Qwen1.5-7B Lora微调报错

  #107 opened 12 days ago by JeckerWen
  2

• peft微调llama3 8b，从第10补开始loss一直都是0

  #124 opened a month ago by ykallan
  6

• 04-Qwen-7B-Chat Lora 微调时报错

  #119 opened a month ago by FisherAndHunter
  2

• 关于代码的组织问题

  #150 opened 9 days ago by RyanOvO
  2

• 华为昇腾服务器的部署方案

  #147 opened 11 days ago by dayphosphor
  2

• WebDemo部署对话如何逐字逐句显示而不是一次性生成

  #149 opened 10 days ago by eternal-bug
  2

• Qwen1.5-7B-Chat vLLM 部署调用-速度测试 hf命令错误

  #101 opened 12 days ago by ericalduo
  1

• 【非Issues！讨论帖】通过lora微调的qianwen和直接使用system来预设的区别貌似不是很大

  #100 opened 12 days ago by Roger-G
  3

• 报错asyncio.run() cannot be called from a running event loop，辛苦大佬们看看

  #97 opened 12 days ago by chaoskklt
  6

• 为什么数据格式化要把输入和输出的合并起来放到input_id?

  #129 opened 18 days ago by lmh0921
  1

• 01-Qwen1.5-7B-Chat FastApi 部署调用.md 传入数据错误

  #128 opened 21 days ago by cqray1990
  1

• 考虑出一些LLM时序预测模型的相关教程吗

  #127 opened 21 days ago by xaxK
  1

• 如懿传

  #126 opened 23 days ago by xixihahahhhhhhhhh
  0

• 请问有多模态LLM的部署/微调文档吗，未来有相关更新计划吗

  #121 opened a month ago by ybshaw
  1

• 模型微调时报错，报内核版本问题 Detected kernel version 5.4.0

  #125 opened a month ago by hgsw
  1

• 微调Qwen1.5-0.5b报错 PermissionError: [Errno 13] Permission denied: './output/Qwen1.5\checkpoint-100'

  #123 opened a month ago by ykallan
  5

• llama3 api报错

  #122 opened a month ago by samprasgit
  1

• 【XVERSE-7B-chat WebDemo 部署】报错 torch.cuda.OutOfMemoryError: CUDA out of memory.

  #113 opened a month ago by hgsw
  2

• deepseek-v2部署请求

  #120 opened a month ago by airsxue
  2

• 在纯 CPU 上可以运行吗？比如苹果电脑没有 cuda?

  #117 opened a month ago by aa03146
  1

• chatglm3,lora微调报错

  #116 opened a month ago by Jsonzhang20
  1

• 我在微调LLAMA3的时候出现NotImplementedError: Cannot copy out of meta tensor; no data!

  #110 opened a month ago by Mr-Lnan
  8

• Qwen1.5-7B Lora微调报错：RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

  #112 opened a month ago by feifeifei-hue
  2

• llama3 API调用的问题

  #114 opened a month ago by 1148514800
  1

• Building wheel for flash-attn (setup.py) ... - 卡住了。

  #99 opened 2 months ago by zhangyc
  4

• InternLM2 缺少包

  #98 opened 2 months ago by JinProton
  2