issues
search
HarderThenHarder
/
transformers_tasks
⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.
https://www.zhihu.com/column/c_1451236880973426688
2.17k
stars
381
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
文本匹配任务Sentence Transformer疑问求解
#90
magicleo
opened
2 months ago
0
文本匹配任务的一些问题
#89
EvanSong77
opened
2 months ago
0
ssl连接失败，无法下载 bert-base-chinese
#88
YKT-668
opened
3 months ago
0
大佬们看到help！！TypeError: tuple indices must be integers or slices, not str
#87
11pomelo
opened
5 months ago
0
求解🙇🏻♀️标注平台打开网页失败 运行streamlit run playground_local.py --server.port 8001
#86
keyilizzie
opened
9 months ago
1
运行UIE train.sh时报错，求解答
#85
keyilizzie
closed
10 months ago
0
关于zero-shot
#84
pengcheng-yan
opened
11 months ago
0
mbti_questions.json 这个测试文件可以分享一下吗
#83
zhongxing-mt
closed
1 year ago
1
发现错误的代码
#82
Victoria-aaaaaa
opened
1 year ago
1
大佬您好，请问在做词表扩充的这个环节，为什么在llama的词表基础上扩充，而不是选择ChatGLM2的分词器
#81
GromZhang
opened
1 year ago
0
基于lora的方式finetune模型后，推理时间很长
#80
wangjiangyue0226
opened
1 year ago
0
请问目前的对于chatglm的微调方法，对于新发布的chatglm2适用吗？
#79
GromZhang
closed
1 year ago
1
关于ptuing
#78
init-neok
opened
1 year ago
4
entity linking基于大模型的方案什么时候放出呢？有计划么
#77
amelieyu
opened
1 year ago
0
fix typo in core.py
#76
eltociear
closed
1 year ago
0
您这里的uie是生成式还是抽取式，cpu速度如何
#75
BEILOP
opened
1 year ago
0
UIE抽取为什么加载不了模型
#74
Smile-shirley
opened
1 year ago
0
PPO中critic模型不是应当使用reward model模型吗？
#73
zhangjian94cn
opened
1 year ago
0
UIE支持uie-m-large吗
#72
liaoweiguo
opened
1 year ago
0
p-tuning 换成英文数据集会报错， raise ValueError(f'Lable Error: "{label}" not in label_dict {list(self.label_dict)}.')
#71
chengturbo
opened
1 year ago
0
where can I download checkpoints/model_1000？
#70
hsauod
opened
1 year ago
3
多卡训练后，推理时提示找不到tokenization_chatglm.py
#69
GromZhang
opened
1 year ago
5
chatglm 微调
#68
xiaogogonuo
opened
1 year ago
0
请问，在您的zeroshot当中，仅仅是通过反馈给模型的history为我们设定的prompt，就完成了某一类的任务问题是吗？
#67
GromZhang
opened
1 year ago
1
在finetune中，请问save_model的时候，是把glm6b的model和lora训练后的model合并成一个了是吗？
#66
GromZhang
closed
1 year ago
7
--mixed_precision=fp16
#65
WGS-note
opened
1 year ago
2
UIE模型train文件运行报错
#64
White-bbb
opened
1 year ago
2
单卡lora微调需要多少显存？
#63
CCzzzzzzz
opened
1 year ago
4
训练时带参数--quantization_bit 4 报错RuntimeError: self and mat2 must have the same dtype
#62
shangzhensen
opened
1 year ago
3
请问数据格式为什么要是把instruct，input，answer这种放在context里面的格式，直接传统的instruct，input，output三元组不行吗，差异在哪里
#61
hangzeli08
opened
1 year ago
1
RuntimeError: CUDA out of memory. Tried to allocate 42.00 MiB (GPU 0; 22.02 GiB total capacity; 20.
#60
chenchaoac
opened
1 year ago
5
请问标注平台是否支持chatglm或者chatrwkv等其他的语言模型
#59
wzsage
opened
1 year ago
0
请问这个repo里的peft代码是做过什么定制化的改动吗？是否可以直接把peft安装到python环境里呢？
#58
zhoujz10
opened
1 year ago
0
Hi,后面会考虑复现基于大模型如bloom、llama的rlhf流程代码？
#57
nieallen
opened
1 year ago
0
关于多卡训练总iter数设置
#56
HXZhong1997
closed
1 year ago
1
考虑支持MOSS吗
#55
BestSongEver
opened
1 year ago
0
关于GLM finetune的OOM
#54
nuoma
opened
1 year ago
0
PET损失函数代码
#53
wuguangshuo
closed
1 year ago
0
多卡训练，无法运行train_multi_gpu.sh
#52
cheney369
opened
1 year ago
1
请问大模型微调需要多少显存？
#51
Crayon-s7
opened
1 year ago
3
模型多卡训练
#50
HocherCN
closed
1 year ago
0
关于词表问题
#49
magnificent1208
opened
1 year ago
0
LLM的finetune需要多大的显存啊？为什么我batch__size调到了1,24g的显存还是不够。。。。。。。
#48
SlothRan
opened
1 year ago
2
关于UIE模型微调，如何进行一机多卡训练？
#47
zhougz2018
opened
1 year ago
2
大模型阅读理解微调
#46
tianchiguaixia
opened
1 year ago
0
ValueError: Attempting to unscale FP16 gradients
#45
magnificent1208
opened
1 year ago
1
能去掉网上的关联吗，每次都要重新下载
#44
magnificent1208
opened
1 year ago
1
UI界面打开提示模型未被定义
#43
kbwzy
opened
1 year ago
6
playground推理过慢
#42
nieallen
opened
1 year ago
2
关于UIE训练效果
#41
shenw8023
opened
1 year ago
1
Next