issues
search
fe1ixxu
/
ALMA
State-of-the-art LLM-based translation models.
MIT License
439
stars
35
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Installation issue
#70
Bostoncake
opened
1 week ago
0
代码问题
#69
ccjjs
opened
1 week ago
0
Ko -> En Bug
#68
sailfish009
opened
3 weeks ago
2
Some questions about alma.
#67
yuanzhiyong1999
opened
3 weeks ago
6
torch.cuda.OutOfMemoryError: CUDA out of memory
#66
risotoonero
closed
2 weeks ago
1
CPO 复现，模型重复输出
#65
XDeepAzure
opened
3 weeks ago
1
Oscar data structure does not match "utils.py" code and datasets module
#64
risotoonero
closed
3 weeks ago
3
Problem with interleave_datasets() for monolingual data fine-tuning
#63
aiyubx
closed
1 month ago
1
finetuning for a specific language
#62
jeff11-1-1
closed
2 weeks ago
1
Release X-ALMA
#61
fe1ixxu
closed
1 month ago
0
Multi Language Translation for More than specified 5 Languages
#60
NavKumarGit
opened
1 month ago
0
Reproduction Issues
#59
soneeee22000
opened
2 months ago
0
Unable to Reproduce ALMA-7b-LoRA Performance, Seeking Assistance
#58
liangyingshao
opened
2 months ago
6
error on pretraining
#57
tsbiosky
opened
2 months ago
1
Issues with Translation Quality Using ALMA/ALMA-R Models on Multi-Domain Dataset
#56
cocaer
closed
3 months ago
2
GPUs used during parallel data fine-tuning
#55
liangyingshao
closed
3 months ago
1
i change the sh for evaluate my data ,but met error
#54
DengNingyuan
opened
4 months ago
0
torch版本问题
#53
DengNingyuan
opened
4 months ago
0
Unknown source language
#52
noahdasanaike
opened
4 months ago
0
predict problem
#51
leee-SeungHyeon
opened
5 months ago
0
Fail to load ALMA-13B
#50
wygao8
closed
2 months ago
1
A shout out to SimPO
#49
fe1ixxu
closed
5 months ago
0
citation for CPO paper
#48
kashif
closed
3 months ago
1
Questions about Inference
#47
kira-lin
closed
5 months ago
1
preprocess_cpo_data
#46
martimfasantos
closed
5 months ago
1
Question about ALMA(R)
#45
mru4913
closed
5 months ago
2
CPO question
#44
gongye19
opened
6 months ago
2
OSError: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory
#43
gongye19
opened
6 months ago
2
OOM 问题, 显卡是A00 40G
#42
gongye19
opened
6 months ago
5
单语数据集的构建
#41
ywlq
closed
7 months ago
2
[Question] Exception during parallel data finetuning
#40
aiyubx
closed
7 months ago
1
Error on running the evaluation command
#39
Amrit-Bhaskar-abhask10
opened
7 months ago
2
No such file or directory
#38
hxue3
opened
8 months ago
0
Training metrics currently not logged?
#37
SirRob1997
opened
8 months ago
2
Question on cpo loss
#36
vince62s
closed
7 months ago
1
[Bug/Feature] The dataset isn't reading the same cache_dir
#35
alvations
closed
3 months ago
2
[Question] Replicating ALMA by training from scratch
#34
alvations
closed
8 months ago
2
Got Errors when pretraining LLaMA-2 on Monolingual Dataset
#33
vhientran
closed
8 months ago
4
Pretraining inquiry.
#32
gyupro
closed
8 months ago
3
Runing parallel_ft_lora.sh
#31
zhengkid
closed
9 months ago
2
Loading ALMA-7B-R (LORA merged) through huggingface downloads Pretrained + LORA
#30
tranvaj
closed
8 months ago
1
A couple of questions for your theory
#29
gyupro
closed
8 months ago
2
Using custom monolingual data instead of OSCAR dataset
#28
learnercat
closed
9 months ago
3
How much parallel data?
#27
zidsi
closed
8 months ago
1
How much CPO data set is expected to be needed when creating a one-to-one machine translator?
#26
qwopqwop200
closed
9 months ago
3
running `runs/parallel_ft_lora.sh`gives overflow
#25
hndrstwn
closed
9 months ago
3
Incomplete Translation from English to Chinese although `max_tokens` is enough
#24
DeyangKong
closed
9 months ago
3
Fine-tuning on longer contexts for better performance?
#23
NilanEkanayake
closed
9 months ago
1
</s> or eos needed for other base models?
#22
zidsi
closed
9 months ago
2
DPODataCollatorWithPadding( TypeError: __init__() got an unexpected keyword argument 'max_length'
#21
sahsaeedi
closed
9 months ago
2
Next