IDEA-CCNL/Fengshenbang-LM
Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系,成为中文AIGC和认知智能的基础设施。
PythonApache-2.0
Issues
- 1
训练一个LongformerForSequenceClassification模型,报错
#413 opened by haonit - 2
- 1
Lyrics 啥时候公开
#451 opened 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 by mario0718 - 0
ziya2-13b-base协议问题
#458 opened by qiantongyu - 1
当我使用Ubert进行实体抽取的微调后,测试集指标问题。
#457 opened by xjDUAN184 - 0
ziya_llama 切分tp后模型卡死,各位大佬有解决方法吗
#456 opened by buringslyar - 0
- 0
- 1
fintune后加载推理报错,用法是标准的用法
#436 opened by o-github-o - 1
finetune_taiyi_stable_diffusion 多卡怎么设置
#435 opened by o-github-o - 0
Deberta 预训练的输出如何使用
#453 opened by yuzicx - 0
Taiyi-CLIP-Roberta-102M-Chinese Finetuning报错
#452 opened by 1306825592 - 2
from modeling_deltalm import DeltalmForConditionalGeneration报错 no known parent package
#443 opened by heiheiheibj - 1
questions about the padding value
#414 opened by iridescentee - 0
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 by zhangheyi-1 - 1
- 5
ziya2预训练的语料拼接是如何通过attention mask规避的
#444 opened by linyubupa - 0
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 by LY637 - 1
燃灯-denoising系列没有开源出来预训练代码吗?
#447 opened 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 by Johnny-xyz - 1
- 1
- 0
TypeError: not a string
#440 opened by neobie - 1
关于Uniex 的span
#439 opened by zizhec - 1
- 1
Ziya2-13B-Chat怎么流式输出
#428 opened by Dingxiangxiang - 0
UniMC对于选项位置敏感的问题
#437 opened by shuopwang - 1
Randeng-Pegasus-523M-Summary-Chinese demo 推理代码有两个问题
#426 opened by twwch - 0
原先transformers的训练脚本中,
#433 opened by ShayDuane - 0
导入 fengshen module 后trainer的进度不显示了
#434 opened by ShayDuane - 0
执行uniex的example.py报错
#432 opened by LANSEYOUYUMOWANG - 0
Erlangshen embedding模型推理使用
#431 opened by Congcong-Song - 0
There is an error installing fengshen package.
#430 opened by Hubotcoder - 0
怎么微调UniMC模型
#429 opened by qinzhiliang - 0
封神榜
#427 opened by yemingshen - 0
中文生成代码评测问题
#425 opened by young-chao - 1
uniex训练时速度很快,但是测试时候速度很慢
#424 opened by miaomiao1215 - 0
qa_t5问题
#423 opened by qaz123wsx456edc789 - 5
Erlangshen-DeBERTa-v2-97M-CWS-Chinese无法加载tokenizer
#409 opened by JaheimLee - 0
- 2
README 很中二
#417 opened by tpoisonooo - 0
基于llama2的子牙13b啥时候发布呢?
#420 opened 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 by xyw7 - 0
- 5
使用微调finetune_taiyi_stable_diffusion/finetune.py出现的bug信息
#412 opened by TTyb - 1
KeyError: 'global_step'
#411 opened by TTyb - 0
- 0
BLIP详细信息?
#410 opened by FutureWithoutEnding - 0
微调taiyi时缺少config.json
#408 opened by sunxiaoyu12