IDEA-CCNL/Fengshenbang-LM

Issues

• 使用二郎神DebertaV2无法复现实验

  #471 opened a month ago by Wang-ck123
  0

• 想要在新版本的transformers中用PegasusTokenizer

  #470 opened a month ago by CurtainRight
  0

• 使用Randeng-Pegasus-523M-Summary-Chinese生成摘要报错PegasusTokenizer' object has no attribute 'vocab

  #461 opened 9 months ago by flystarts
  2

• 为什么不公开情感分析EPRSTMT的代码

  #469 opened 3 months ago by yinsuhao
  0

• 请问句子嵌入模型 IDEA-CCNL/Erlangshen-TCBert-1.3B-Sentence-Embedding-Chinese 能不能用 sbert来加载？

  #468 opened 5 months ago by qiulang
  0

• 请问Uniex模型中FastExtractModel和ExtractModel这两个类有什么区别？fast_ex_mode参数的作用以及和他们的关系？

  #467 opened 6 months ago by tjhwk
  0

• 大佬可以训练一个像jina-clip-v1的中文版这样的话，以后做搜索或是 构建多模态 RAG 应用 就牛了~~

  #466 opened 7 months ago by gg22mm
  0

• Sentiment Evaluation Metric (F1 vs. Accuracy)

  #464 opened 7 months ago by yidinghao
  0

• finetune_taiyi_stable_diffusion 最简单的办法 - 是否可以把 CLIPTextModel 与 CLIPTokenizer 训练模型单独训练并发布在 huggingface上 ， 后面用下面代码即可调用

  #462 opened 9 months ago by gg22mm
  0

• Erlangshen-Roberta-110M-Similarity训练用数据集

  #441 opened a year ago by a-small-green-cabbage
  2

• Lyrics 啥时候公开

  #451 opened a year ago by zzf-damon
  1

• 用dreambooth训练模型后，加载stable-diffusion-webui日志出现'BertEmbeddings' object has no attribute 'token_embedding'错误

  #459 opened a year ago by mario0718
  1

• ziya2-13b-base协议问题

  #458 opened a year ago by qiantongyu
  0

• 当我使用Ubert进行实体抽取的微调后，测试集指标问题。

  #457 opened a year ago by xjDUAN184
  1

• ziya_llama 切分tp后模型卡死，各位大佬有解决方法吗

  #456 opened a year ago by buringslyar
  0

• 太乙IDEA-CCNL/Taiyi-CLIP-Roberta-102M-Chinese在训练的过程如何做到中英文兼顾的？

  #455 opened a year ago by Klaus-Chow
  0

• 按照 README 微调太乙的 stable-diffusion 模型后，利用from_pretrained() 方法加载模型出错.

  #454 opened a year ago by hermanWu55
  0

• fintune后加载推理报错，用法是标准的用法

  #436 opened a year ago by o-github-o
  1

• finetune_taiyi_stable_diffusion 多卡怎么设置

  #435 opened a year ago by o-github-o
  1

• Deberta 预训练的输出如何使用

  #453 opened a year ago by yuzicx
  0

• Taiyi-CLIP-Roberta-102M-Chinese Finetuning报错

  #452 opened a year ago by 1306825592
  0

• from modeling_deltalm import DeltalmForConditionalGeneration报错 no known parent package

  #443 opened a year ago by heiheiheibj
  2

• 合并ziya模型后生成safetensors格式文件，应该如何转化为.bin的格式呢

  #450 opened a year ago by zhangheyi-1
  0

• 试着合并huggingface上的ziya-llama-v1差值模型与原始llama-13b模型，合并之后的模型generate全是乱码

  #422 opened a year ago by jamestang0219
  1

• ziya2预训练的语料拼接是如何通过attention mask规避的

  #444 opened a year ago by linyubupa
  5

• OSError: Can't load tokenizer for 'IDEA-CCNL/Randeng-Transformer-1.1B-Denoise'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'IDEA-CCNL/Randeng-Transformer-1.1B-Denoise' is the correct path to a directory containing all relevant files for a TransfoXLDenoiseTokenizer tokenizer.

  #448 opened a year ago by LY637
  0

• 燃灯-denoising系列没有开源出来预训练代码吗？

  #447 opened a year ago by LY637
  1

• Ziya-Reader-13B-v1.0长度限制4-8K，请问LongBench中文多文档QA问题都是8K-27K，是如何测评的，采用首尾截断，还是重新构造了数据集？

  #442 opened a year ago by Johnny-xyz
  1

• 配合ziya-reader使用的ziya-embedding和ziya-searching-agent在哪

  #445 opened a year ago by Mr-IT007
  1

• Anyone can help me with the "Randeng-BART-139M-SUMMARY" fine-tuning?

  #446 opened a year ago by loveplay1983
  1

• TypeError: not a string

  #440 opened a year ago by neobie
  0

• 关于Uniex 的span

  #439 opened a year ago by zizhec
  1

• Ziya-Coding-15B-v1 预测输出也会把问题重新输出一遍，影响预测速度，请问这改怎么解决？

  #438 opened a year ago by IT-Xue
  1

• Ziya2-13B-Chat怎么流式输出

  #428 opened a year ago by Dingxiangxiang
  1

• UniMC对于选项位置敏感的问题

  #437 opened a year ago by shuopwang
  0

• Randeng-Pegasus-523M-Summary-Chinese demo 推理代码有两个问题

  #426 opened a year ago by twwch
  1

• 原先transformers的训练脚本中，

  #433 opened a year ago by ShayDuane
  0

• 导入 fengshen module 后trainer的进度不显示了

  #434 opened a year ago by ShayDuane
  0

• 执行uniex的example.py报错

  #432 opened a year ago by LANSEYOUYUMOWANG
  0

• Erlangshen embedding模型推理使用

  #431 opened a year ago by Congcong-Song
  0

• There is an error installing fengshen package.

  #430 opened a year ago by Hubotcoder
  0

• 怎么微调UniMC模型

  #429 opened a year ago by qinzhiliang
  0

• 封神榜

  #427 opened a year ago by yemingshen
  0

• 中文生成代码评测问题

  #425 opened a year ago by young-chao
  0

• uniex训练时速度很快，但是测试时候速度很慢

  #424 opened a year ago by miaomiao1215
  1

• qa_t5问题

  #423 opened a year ago by qaz123wsx456edc789
  0

• 使用load_in_8bit和device_map='auto'加载Ziya-BLIP2-14B-Visual-v1会报错

  #421 opened a year ago by WanBenLe
  0

• 基于llama2的子牙13b啥时候发布呢？

  #420 opened a year ago by xxm1668
  0

• 请问可以开源出来训练Ziya-BLIP2-14B-Visual-v1的2000w高质量中文数据集吗？

  #419 opened 2 years ago by xyw7
  0

• AttributeError: 'LlamaConfig' object has no attribute 'attention_config'

  #418 opened 2 years ago by mycutedog
  0