issues
search
shibing624
/
textgen
TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet and so on. 文本生成模型，实现了包括LLaMA，ChatGLM，BLOOM，GPT2，Seq2Seq，BART，T5，UDA等模型的训练和预测，开箱即用。
Apache License 2.0
937
stars
109
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
training_copyt5_model_demo.py
#60
ytWu1314
closed
2 months ago
3
部署问题
#59
yeyuan0620
opened
2 months ago
4
大佬请问有没有针对chatglm3的评估脚本呀
#58
Franklin-L
closed
7 months ago
3
BART、T5和GPT2的模型输入问题
#57
YunweiDai
opened
1 year ago
0
gpt2训练学不到东西
#56
Lxhnnn
opened
1 year ago
2
大老看了您的微调方式，有点疑问，您的三个阶段是在哪里体现出来的？
#55
gg22mm
closed
1 year ago
2
大佬什么时候支持一个chatRwkv, 这个现在用的人那么火，不搞一下
#54
gg22mm
opened
1 year ago
2
模型结果有问题
#53
chw-shuai
closed
1 year ago
1
Fixed bug: Handle error when CUDA is not available
#52
alitrack
closed
1 year ago
0
是否支持ChatGLM2-6b的微调？
#51
svjack
opened
1 year ago
2
merge other to me
#50
manutd12
closed
1 year ago
0
bart纠错模型训练问题
#49
EASTERNTIGER
closed
1 year ago
2
1. README文档的微信群和几个别的超链接打不开 2. 开始写使用教程（大概更新会比较慢）
#48
PolarisRisingWar
opened
1 year ago
1
torch.load()希望能够增加map_location
#47
PolarisRisingWar
opened
1 year ago
4
README中LLaMA模型部分是不是还没有更新+merge_peft_adapter.py的save_pretrained()似乎有问题
#46
PolarisRisingWar
closed
1 year ago
1
希望作者可以将最新的Aquila-7B和baichuan-7B模型集成进来
#45
AILWQ
opened
1 year ago
9
ChatGLM-6B full parameter fine-tuning loss = 0
#44
xiaojunjun65
closed
1 year ago
1
how to use qlora ?
#43
feng-1985
opened
1 year ago
5
hello master，BLOOM 模型 目前支持单机多卡训练么，如果支持是
#42
116705792
opened
1 year ago
3
模型训练出错
#41
svjack
closed
1 year ago
9
lora 训练参数
#40
MonkeyTB
opened
1 year ago
3
多卡部署
#39
ZTurboX
opened
1 year ago
3
关于数据集处理
#37
kostya-sec
opened
1 year ago
4
NotImplementedError: Cannot copy out of meta tensor; no data!
#36
LMXKO
closed
1 year ago
3
merge
#35
manutd12
closed
1 year ago
0
安装问题
#34
chengturbo
opened
1 year ago
2
保存模型问题
#33
MonkeyTB
closed
1 year ago
2
ImportError: cannot import name 'ChatGlmModel' from 'textgen'
#32
888yyh
closed
1 year ago
1
请教一下Chinese-Alpaca-Plus-13B继续做peft微调需要多少显存？
#31
bash99
opened
1 year ago
4
请问您的ptuning是V1吗，现在支持ptuning V2吗，不知道哪个在生成上好一点。您的几个微调方法lora，adalora，ptuning哪个效果好啊，full-finetuning一把学习率是多少啊～
#30
hangzeli08
opened
1 year ago
3
用lora训练chatglm时跑内存
#29
NefelibataJay
closed
1 year ago
8
单机多卡训练方法
#28
hangzeli08
closed
6 months ago
4
chatglm用lora训练完predict出的结果和重新加载模型和lora后输出的结果差异很大
#27
hongyix
closed
1 year ago
15
请问有没有用于evaluation的代码？
#26
xiongxiaochu
closed
1 year ago
12
pad labels to max length
#25
xingener
closed
1 year ago
0
作者大哥，请问可以让chatglm系列支持单机多卡吗，改了一下午，改崩溃了，终于可以训练了，但是保存不了··· 你来吧
#24
hangzeli08
closed
1 year ago
2
请问作者的学习率用的是多少啊，梯度下降方式呢，warmup步数呢，方便公开训练脚本参数吗
#23
hangzeli08
closed
1 year ago
1
model 使用授权问题
#22
wzg-zhuo
closed
1 year ago
1
如何用使用 p40 训练lora
#21
hongyix
closed
1 year ago
2
怎么指定单GPU
#20
MonkeyTB
opened
1 year ago
11
ChatGLM模型微调问题咨询
#19
alexhmyang
opened
1 year ago
34
如果我想训练一个细分领域的知识库，请问 训练数据 要按什么格式准备?您的例子给的是 纠正拼写错误，我们 知识库 训练需要改动哪些地方才能正确训练？
#18
alexhmyang
closed
1 year ago
1
读取数据问题
#17
MonkeyTB
opened
1 year ago
15
Miss Requirement tensorboardX
#16
bash99
closed
1 year ago
8
请问chatglm with lora 什么时候支持多卡fine tune啊
#15
Zarc98
opened
1 year ago
6
Bart长文本训练问题
#14
YoungChanYY
opened
1 year ago
5
shibing624/prompt-t5-base-chinese测试结果和示例结果不一致
#13
hjing100
closed
1 year ago
2
请问训练的数据集如何获取啊？
#12
p-moon
closed
11 months ago
5
T5、GPT用于文本翻译的句式在那个文件
#11
vikey
closed
1 year ago
2
想要开启GPU上训练的话咋设置？
#10
huyi1989
closed
2 years ago
1
Next