project-baize/baize-chatbot

Issues

• ValueError: The model did not return a loss from the inputs, only the following keys: logits. For reference, the inputs it received are input_ids,attention_mask.

  #62 opened 3 months ago by yaolu-zjut
  0

• How to solve ImportError: cannot import name 'BaseCache' from 'langchain'？如何解决ImportError？Following are the details. 报错细节见下。

  #60 opened a year ago by PoisonousBromineChan
  3

• License

  #59 opened a year ago by fakerybakery
  0

• Is this a typo in preprocess.py?

  #57 opened a year ago by abdullin
  0

• How about Chinese performance

  #55 opened 2 years ago by yuanzhiyong1999
  0

• AttributeError: 'NoneType' object has no attribute 'view'

  #53 opened 2 years ago by Amit507017
  1

• TypeError: init() got an unexpected keyword argument 'torch_dtype

  #52 opened 2 years ago by lidongxing
  1

• What format is the multi-round session input training？

  #50 opened 2 years ago by Wzhsgsg
  1

• ValueError: Can't find 'adapter_config.json' at 'project-baize/baize-lora-7B'

  #51 opened 2 years ago by tryharder31
  1

• Typo of the Github link on huggingface

  #54 opened 2 years ago by g-h-chen
  0

• v2 dataset request

  #48 opened 2 years ago by arch-btw
  1

• where is the loss code?

  #49 opened 2 years ago by royshan
  1

• Features : Can it use 4 bit QLORA ?

  #46 opened 2 years ago by x4080
  2

• SDF, how does it work?

  #45 opened 2 years ago by qrdlgit
  5

• Dr. LLaMA: Improving Small Language Models in Domain-Specific QA via Generative Data Augmentation

  #44 opened 2 years ago by qrdlgit
  0

• How to implement multi-gpu training

  #43 opened 2 years ago by chlinfeng1997
  0

• How to implement multi-gpu training

  #42 opened 2 years ago by chlinfeng1997
  0

• try train 25G data/quora_chat_data failed

  #41 opened 2 years ago by yfq512
  1

• how to use the specified gpu？

  #40 opened 2 years ago by xingshuoli
  2

• very high CPU during inference. GPU seems to be idle.

  #39 opened 2 years ago by xuduo18
  1

• Dutch Quora, Stack Overflow, Alpaca dataset released

  #34 opened 2 years ago by BramVanroy
  3

• Weird Reported Memory Usage

  #26 opened 2 years ago by Lyken17
  3

• Cost of data?

  #22 opened 2 years ago by raihan0824
  1

• run app.py error

  #14 opened 2 years ago by XvHaidong
  8

• train my own data, answers are not very accurate.

  #36 opened 2 years ago by yfq512
  1

• Failed to import transformers.trainer because of the following error

  #24 opened 2 years ago by yangp725
  1

• what exact version of transformers do you use?

  #35 opened 2 years ago by zixiliuUSC
  1

• gptq 4-bit quantized version

  #17 opened 2 years ago by regstuff
  3

• How to generate chat data with FAQ dataset

  #33 opened 2 years ago by xueyouluo
  1

• 30B failed, pytorch_model-00039-of-00061.bin, If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.

  #31 opened 2 years ago by LIO-H-ZEN
  1

• Strange results for a simple question - Baize-7B

  #32 opened 2 years ago by arch-btw
  1

• Performance cannot align with demo

  #28 opened 2 years ago by LIO-H-ZEN
  3

• Errors running 13b 8bit

  #23 opened 2 years ago by gamerscomplete
  9

• generated results are terrible with bloom

  #30 opened 2 years ago by raihan0824
  4

• "fix dark mode" in hugging face🤗 and for local demo

  #27 opened 2 years ago by Keldos-Li
  2

• sharegpt 90k data

  #25 opened 2 years ago by zedom1
  2

• How collect other topic data?

  #19 opened 2 years ago by yfq512
  7

• Does prob_sum in greedy search always add up to 1?

  #18 opened 2 years ago by qrdlgit
  1

• Is it possible to train Chinese data directly based on English models?

  #21 opened 2 years ago by yfq512
  1

• Why not use huggingface generate() and write custom greedy search?

  #12 opened 2 years ago by Moses0h
  3

• Encountering error: app.py has "cannot import name 'LlamaForCausalLM' from 'transformers'"

  #10 opened 2 years ago by koolkao
  6

• Controlling the output

  #16 opened 2 years ago by raihan0824
  3

• get bug when use finetune code

  #7 opened 2 years ago by AItechnology
  2

• How to access int8 with 13b version?

  #15 opened 2 years ago by Meathelix1
  1

• Baize repeating answer mutilple times

  #5 opened 2 years ago by LxDevelop
  2

• Issue Running App After First Shutdown.

  #13 opened 2 years ago by Meathelix1
  2

• Langchain and Llama Index?

  #9 opened 2 years ago by Meathelix1
  0

• Error when running

  #8 opened 2 years ago by Meathelix1
  2

• 1

  #6 opened 2 years ago by cowmix
  0

• I see Error after any first message into UI

  #4 opened 2 years ago by bymihaj
  1