issues
search
DachengLi1
/
LongChat
Official repository for LongChat and LongEval
Apache License 2.0
500
stars
29
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Fix BibTeX
#44
sylchw
opened
1 month ago
0
lmsys/longchat-7b-v1.5-32k is a base model or a aligned model?
#43
hsiehjackson
opened
4 months ago
0
How to prepare the training data
#42
ycsun1972
opened
10 months ago
2
Added additional testcases
#41
AnzeXie
closed
10 months ago
0
dummy conversations seem to be short
#40
Arist12
closed
10 months ago
2
Inference is very slow on long text input
#39
Colafei0406
opened
10 months ago
1
support vllm & lightllm
#38
andy-yang-1
closed
11 months ago
3
license
#37
yzhang123
closed
9 months ago
1
Release LongChat v1.5
#36
DachengLi1
closed
11 months ago
0
Hi, using xformers monkey patch training llama2 got loss explosion
#35
lucasjinreal
opened
11 months ago
0
Update Anthropic Client
#34
krrishdholakia
opened
11 months ago
2
flash attention rename
#33
Arist12
closed
11 months ago
1
Do you support Llama-2-13b model data?
#32
brewswang
opened
11 months ago
0
train ValueError
#31
brewswang
opened
11 months ago
0
flash_attn installed, but got ImportErrorImportError
#30
brewswang
closed
11 months ago
4
Output token limit
#29
MoppyDu97
opened
11 months ago
0
OOM issue
#28
WeixuanXiong
closed
11 months ago
4
Why the use of flash attention in the inference stage will lead to slower?
#27
xyfZzz
closed
11 months ago
2
Maybe a bug in the preprocess?
#26
Richar-Du
opened
1 year ago
3
About the print message
#25
lucasjinreal
opened
1 year ago
2
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
#24
ChaoyuHuang
opened
1 year ago
0
Longchat inference configuration
#23
SeekWrldTea
opened
1 year ago
1
Use attention_mask and use_cache for xformers
#22
fahadh4ilyas
closed
1 year ago
0
Xformers Monkey Patch Compatibility
#21
fahadh4ilyas
opened
1 year ago
1
Support for other model like Baichuan
#20
lucasjinreal
opened
1 year ago
0
About the learning rate
#19
lucasjinreal
opened
1 year ago
1
Will it support qlora?
#18
lw3259111
opened
1 year ago
1
The purpose of pretrain script?
#17
fahadh4ilyas
closed
1 year ago
2
why not reuse fschat code?
#16
lucasjinreal
closed
1 year ago
8
Monkey Patch Xformers use `past_key_value` but `use_cache` can't be `True`?
#15
fahadh4ilyas
closed
1 year ago
9
longchat-13b-16k chat not work
#14
ahkimkoo
opened
1 year ago
9
Implementation for issue 6&7
#13
AnzeXie
closed
1 year ago
0
Web GUI for longchat
#12
VVNMA
opened
1 year ago
3
Multi-node training?
#11
XueFuzhao
closed
1 year ago
1
Load the model for inference?
#10
fahadh4ilyas
closed
1 year ago
4
OutOfMemoryError: CUDA out of memory.
#9
brewswang
opened
1 year ago
5
Can inference be run on consumer hardware?
#8
GrahamboJangles
opened
1 year ago
8
Add scripts on querying closed sourced models
#7
DachengLi1
closed
1 year ago
1
Add scripts to generate more testcases
#6
DachengLi1
closed
1 year ago
1
How was the 18k dataset prepared?
#5
musabgultekin
closed
1 year ago
3
How to use 3090 to train 16k model?
#4
aresa7796
opened
1 year ago
7
Add support for flash attention with use_cache
#3
DachengLi1
opened
1 year ago
1
unsupervised pre-training on the model
#2
wqn1
closed
1 year ago
5
[DO NOT MERGE] Add ZeroScrolls & Scrolls Evals
#1
Ying1123
opened
1 year ago
0