Skip to content

Issues: LianjiaTech/BELLE

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

97 Open 338 Closed
97 Open 338 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

large-v3-zh中文的效果变得更差了
#584 opened May 6, 2024 by llkongs
1
belle-whisper model take much more time even after transformed by ctranslate
#583 opened Apr 26, 2024 by yurinapoleon
can we fine-tunning on belle-whisper model
#582 opened Apr 25, 2024 by yurinapoleon
生成特定领域的高质量数据集
#581 opened Apr 14, 2024 by lzl-hello
Model inference speed is too slow (positively related to max_new_tokens length)
#580 opened Apr 10, 2024 by SunriseB
镜像不work
#579 opened Apr 9, 2024 by wnf
有没有ggml模型呀？
#576 opened Feb 12, 2024 by DancingLeaf123
关于Belle-whisper-large-v2-zh模型分句的问题，请问这个模型是用有时间戳的分句数据训练的吗？
#575 opened Feb 2, 2024 by houmochenliu
2
用BELLE-2/Belle-whisper-large-v2-zh识别中文音频，效果还不如Systran/faster-whisper-large-v2？
#574 opened Feb 2, 2024 by drilistbox
11
BELLE/train/src/models/generation_utils.py这个文件不是只有transformers<=4.30.2时使用自定义的trainer.py才会触发吗？但里面generation_utils.py为啥有4.30.2版本以上的东西，训练报错：ImportError: cannot import name 'SequenceBiasLogitsProcessor' from 'transformers.generation.logits_process'
#562 opened Dec 21, 2023 by Julylmm
请问：论文中预训练采用的MIP训练方式的效果，大家在其他领域有验证过效果吗？
#561 opened Dec 18, 2023 by CaptainDP
1
Is there any prompt examples of using BELEE for persona-based dialogue generation?
#559 opened Dec 15, 2023 by iamlxb3
12块8G显存可以用来训练吗
#540 opened Oct 13, 2023 by grainw
【模型训练】我想请问模型输出的文件应该怎么看，每个文件都是什么作用呢？
#538 opened Oct 10, 2023 by zzisbeauty
使用run_pt.sh进行lora的非指令微调，没有效果。
#536 opened Oct 8, 2023 by fanxptj
indices should be either on cpu or on the same device as the indexed tensor (cpu)
#508 opened Sep 11, 2023 by zzisbeauty
利用Belle生成数据集
#505 opened Sep 10, 2023 by tuqingwen
data_set 报错
#498 opened Aug 25, 2023 by wangyiyang
python generate_instruction.py generate_instruction_following_data 进度为0
#496 opened Aug 21, 2023 by whm233
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xa5 in position 191: invalid start byte
#495 opened Aug 19, 2023 by sth0114
推理时找不到adapter_config.json文件
#492 opened Aug 16, 2023 by jerryzz668
AutoTokenizer vs. LlamaTokenizer
#490 opened Aug 14, 2023 by joe-kwon-lg
你好，关于我模型训练一天，但进度只有1%，这样的速度正常吗？
#484 opened Aug 9, 2023 by tomhas-hub
Hope to get in touch
#483 opened Aug 9, 2023 by JimmyMa99
BELLE-0.5M-CLEAN是否开源
#482 opened Aug 8, 2023 by liudayiheng
ProTip! Add no:assignee to see everything that’s not assigned.