issues
search
beyondguo
/
LLM-Tuning
Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.
967
stars
99
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
ImportError: dlopen: cannot load any more object with static TLS
#59
hjing100
opened
6 months ago
1
Why epoch in log is different from progress
#58
jimmy-walker
opened
10 months ago
0
使用ChatGLM2-6B分词报错
#57
kyle-hy
opened
1 year ago
0
code lamma微调脚本可以使用baichuan2的吗
#56
xhaoss
opened
1 year ago
0
model.hf_device_map 不存在如何解决呢
#55
LivinLuo1993
opened
1 year ago
0
按照教程,一步一步弄的,到了训练PPO的时候, 卡到 CUDA error: device-side assert triggered
#54
karl-tao-zhang
opened
1 year ago
3
where is "my_templates" module
#53
andyzhu
opened
1 year ago
0
PPO training CUDA out of memory
#52
14H034160212
opened
1 year ago
0
为什么ppo model 需要接AutoModelForCausalLMWithValueHead呢？
#51
jiahuanluo
opened
1 year ago
1
chatglt-6b2 lora微调使用int4精度报错
#50
hehuomu
opened
1 year ago
0
chaglm-6b lora微调执行到指定的eval_step后提示“iteration over a 0-d tensor”
#49
LivinLuo1993
opened
1 year ago
1
baichuan-13b reward model训练
#48
endlesstalking
opened
1 year ago
0
加载数据集报错
#47
endlesstalking
closed
1 year ago
1
chatglm2不支持SequenceClassification请问如何解决。。
#46
jaycehw
closed
1 year ago
1
为什么训练阶段的显存一直在往上涨？一会就 OOM 了
#45
Amazing-J
closed
1 year ago
1
baichuan_lora_tuning运行，为什么一直卡在8%呢？
#44
yanduoduan
closed
1 year ago
2
ppo报错
#43
yyy900
closed
1 year ago
3
如何在离线环境生成 tokenized_data ？
#42
seek4self
closed
1 year ago
1
rulai_enhance.json 数据开源了嘛大佬
#41
zlszhonglongshen
closed
1 year ago
1
RuntimeError: Expected is_sm80 to be true, but got false.
#40
Qiang-HU
opened
1 year ago
4
使用lora微调ChatGLM2-6B 报错
#39
QJShan
opened
1 year ago
1
这个微调代码不能直接用来baichuan-13B模型的微调？在13B一直报错
#38
DaiJitao
opened
1 year ago
2
lora tuning 出的权重，再加一个合并的功能？
#37
litetoooooom
opened
1 year ago
1
datasets.builder.DatasetGenerationError: An error occurred while generating the dataset
#36
zlszhonglongshen
closed
1 year ago
1
6块Tesla A100 40G训练会卡住
#35
cherishtttz
closed
1 year ago
1
TORCH_USE_CUDA_DSA
#34
Mrjude
closed
1 year ago
3
是否支持多轮对话的微调？
#33
yaakua
opened
1 year ago
1
glm2和glm分别需要多大的显存才能微调
#32
ShiXiangXiang123
closed
1 year ago
1
微调出错如下：
#31
ShiXiangXiang123
closed
1 year ago
1
cuda版本
#30
1910183821
closed
1 year ago
1
微调的时候如何让模型记住一些特有的知识呢
#29
controZheng
opened
1 year ago
3
关于全量和LoRA的问题
#28
llmrainer
closed
1 year ago
2
请问可以有支持 Apple M 系列处理器 mps 的方式吗？
#27
minjin
closed
1 year ago
1
请教一下显存问题
#25
Jamine-W
closed
1 year ago
3
是否可以增加 预测和推断的代码？
#22
RileyShe
closed
1 year ago
1
请教一个问题，chatglm2在用lora微调时，不添加attention mask也可以么？
#21
annw0922
opened
1 year ago
2
Chinese-LLaMA-Alpaca有计划安排加入吗？
#20
SilenceWinter
opened
1 year ago
1
微调后输出长度不够长
#19
dragononly
closed
1 year ago
1
多卡训练感觉不是并发的?
#18
shenmadouyaowen
opened
1 year ago
8
训练后加载跑,无效果,请看看这样对吗
#17
dragononly
opened
1 year ago
0
weights 文件训练出来很小，正常嘛
#16
dragononly
closed
1 year ago
1
chatglm2报错：ValueError: weight is on the meta device, we need a `value` to put in on 0
#15
angel1288
opened
1 year ago
3
ChatGLM2按照readme教程微调了，但是没有效果！！！
#14
HelixPark
opened
1 year ago
19
如何评估finetune过程中模型的性能？
#13
dxyzx0
closed
1 year ago
2
看了#8号贴，注释了两行报119
#12
BoFan-tunning
closed
1 year ago
0
chatglm2_loar_tuning run raise NotImplementedError
#11
xieyongshuai
opened
1 year ago
7
报错“KeyError: 'transformer.embedding'”
#10
lilulu0702
opened
1 year ago
3
有群吗,拉个群把
#9
dragononly
closed
1 year ago
2
运行报错
#8
shenmadouyaowen
closed
1 year ago
22
怎么训练多轮对话呀
#7
liuhuapiaoyuan
opened
1 year ago
5
Next