Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / project-baize/baize-chatbot issues and pull requests
#62 - 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.
Issue -
State: open - Opened by yaolu-zjut 19 days ago
#61 - update install from source link
Pull Request -
State: open - Opened by kghamilton89 7 months ago
#60 - 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。
Issue -
State: open - Opened by PoisonousBromineChan 10 months ago
- 3 comments
#59 - License
Issue -
State: open - Opened by fakerybakery 10 months ago
#58 - fix ai_token method in collect_v2.py
Pull Request -
State: open - Opened by Miraclemin about 1 year ago
#57 - Is this a typo in preprocess.py?
Issue -
State: open - Opened by abdullin about 1 year ago
#55 - How about Chinese performance
Issue -
State: open - Opened by yuanzhiyong1999 over 1 year ago
#54 - Typo of the Github link on huggingface
Issue -
State: open - Opened by g-h-chen over 1 year ago
#53 - AttributeError: 'NoneType' object has no attribute 'view'
Issue -
State: open - Opened by Amit507017 over 1 year ago
- 1 comment
#52 - TypeError: init() got an unexpected keyword argument 'torch_dtype
Issue -
State: open - Opened by lidongxing over 1 year ago
- 1 comment
#51 - ValueError: Can't find 'adapter_config.json' at 'project-baize/baize-lora-7B'
Issue -
State: open - Opened by tryharder31 over 1 year ago
- 1 comment
#50 - What format is the multi-round session input training?
Issue -
State: open - Opened by Wzhsgsg over 1 year ago
- 1 comment
#49 - where is the loss code?
Issue -
State: open - Opened by royshan over 1 year ago
- 1 comment
#48 - v2 dataset request
Issue -
State: open - Opened by arch-btw over 1 year ago
- 1 comment
#46 - Features : Can it use 4 bit QLORA ?
Issue -
State: open - Opened by x4080 over 1 year ago
- 2 comments
#45 - SDF, how does it work?
Issue -
State: open - Opened by qrdlgit over 1 year ago
- 5 comments
#44 - Dr. LLaMA: Improving Small Language Models in Domain-Specific QA via Generative Data Augmentation
Issue -
State: open - Opened by qrdlgit over 1 year ago
#43 - How to implement multi-gpu training
Issue -
State: closed - Opened by chlinfeng1997 over 1 year ago
#42 - How to implement multi-gpu training
Issue -
State: open - Opened by chlinfeng1997 over 1 year ago
#41 - try train 25G data/quora_chat_data failed
Issue -
State: open - Opened by yfq512 over 1 year ago
- 1 comment
#40 - how to use the specified gpu?
Issue -
State: open - Opened by xingshuoli over 1 year ago
- 2 comments
#39 - very high CPU during inference. GPU seems to be idle.
Issue -
State: open - Opened by xuduo18 over 1 year ago
- 1 comment
#38 - Fauno - Italian version of Baize
Pull Request -
State: closed - Opened by andreabac3 over 1 year ago
- 1 comment
#37 - Update utils.py
Pull Request -
State: closed - Opened by gptbert over 1 year ago
#36 - train my own data, answers are not very accurate.
Issue -
State: open - Opened by yfq512 over 1 year ago
- 1 comment
#35 - what exact version of transformers do you use?
Issue -
State: open - Opened by zixiliuUSC over 1 year ago
- 1 comment
#34 - Dutch Quora, Stack Overflow, Alpaca dataset released
Issue -
State: closed - Opened by BramVanroy over 1 year ago
- 3 comments
#33 - How to generate chat data with FAQ dataset
Issue -
State: closed - Opened by xueyouluo over 1 year ago
- 1 comment
#32 - Strange results for a simple question - Baize-7B
Issue -
State: closed - Opened by arch-btw over 1 year ago
- 1 comment
#31 - 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.
Issue -
State: closed - Opened by LIO-H-ZEN over 1 year ago
- 1 comment
#30 - generated results are terrible with bloom
Issue -
State: open - Opened by raihan0824 over 1 year ago
- 4 comments
#29 - demo: Allow passing in 8bit as an argument
Pull Request -
State: closed - Opened by dnouri over 1 year ago
#28 - Performance cannot align with demo
Issue -
State: closed - Opened by LIO-H-ZEN over 1 year ago
- 3 comments
#27 - "fix dark mode" in hugging face🤗 and for local demo
Issue -
State: open - Opened by Keldos-Li over 1 year ago
- 2 comments
#26 - Weird Reported Memory Usage
Issue -
State: closed - Opened by Lyken17 over 1 year ago
- 3 comments
#25 - sharegpt 90k data
Issue -
State: open - Opened by zedom1 over 1 year ago
- 2 comments
#24 - Failed to import transformers.trainer because of the following error
Issue -
State: closed - Opened by yangp725 over 1 year ago
- 1 comment
#23 - Errors running 13b 8bit
Issue -
State: open - Opened by gamerscomplete over 1 year ago
- 9 comments
#22 - Cost of data?
Issue -
State: closed - Opened by raihan0824 over 1 year ago
- 1 comment
#21 - Is it possible to train Chinese data directly based on English models?
Issue -
State: open - Opened by yfq512 over 1 year ago
- 1 comment
#20 - feat: Add github action
Pull Request -
State: closed - Opened by gaocegege over 1 year ago
- 1 comment
#19 - How collect other topic data?
Issue -
State: open - Opened by yfq512 over 1 year ago
- 7 comments
#18 - Does prob_sum in greedy search always add up to 1?
Issue -
State: open - Opened by qrdlgit over 1 year ago
- 1 comment
#17 - gptq 4-bit quantized version
Issue -
State: open - Opened by regstuff over 1 year ago
- 3 comments
Labels: enhancement
#16 - Controlling the output
Issue -
State: open - Opened by raihan0824 over 1 year ago
- 3 comments
#15 - How to access int8 with 13b version?
Issue -
State: open - Opened by Meathelix1 over 1 year ago
- 1 comment
#14 - run app.py error
Issue -
State: open - Opened by XvHaidong over 1 year ago
- 8 comments
#13 - Issue Running App After First Shutdown.
Issue -
State: closed - Opened by Meathelix1 over 1 year ago
- 2 comments
#12 - Why not use huggingface generate() and write custom greedy search?
Issue -
State: closed - Opened by Moses0h over 1 year ago
- 3 comments
Labels: enhancement
#11 - Update requirements.txt
Pull Request -
State: closed - Opened by cameronbergh over 1 year ago
#10 - Encountering error: app.py has "cannot import name 'LlamaForCausalLM' from 'transformers'"
Issue -
State: open - Opened by koolkao over 1 year ago
- 6 comments
#9 - Langchain and Llama Index?
Issue -
State: open - Opened by Meathelix1 over 1 year ago
Labels: enhancement
#8 - Error when running
Issue -
State: closed - Opened by Meathelix1 over 1 year ago
- 2 comments
#7 - get bug when use finetune code
Issue -
State: closed - Opened by AItechnology over 1 year ago
- 2 comments
#5 - Baize repeating answer mutilple times
Issue -
State: closed - Opened by LxDevelop over 1 year ago
- 2 comments
#4 - I see Error after any first message into UI
Issue -
State: closed - Opened by bymihaj over 1 year ago
- 1 comment
#3 - Please add minimal system requirements for starting system on local PC
Issue -
State: closed - Opened by bymihaj over 1 year ago
- 2 comments
#2 - was trying this on gpt-j-6b but landed into error on finetuning
Issue -
State: open - Opened by allthingssecurity over 1 year ago
- 1 comment
#1 - Adding support to https://github.com/NolanoOrg/cformers
Issue -
State: closed - Opened by tejasvaidhyadev over 1 year ago