issues
search
microsoft
/
LLMLingua
To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
https://llmlingua.com/
MIT License
4.17k
stars
222
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Feature(LLMLingua): add MInference News
#166
iofu728
closed
3 days ago
0
[Question]: Token indices sequence length is longer than the specified maximum sequence length for this model (614 > 512). Running this sequence through the model will result in indexing errors
#165
lifengyu2005
opened
2 weeks ago
1
Experiments[Question]:
#164
520zw
closed
2 weeks ago
2
[Question]: longbench数据集测试对context和question的压缩
#163
Diana303068
opened
1 month ago
2
[Question]: How to combine longllmlingua and llmlingua2 ?
#162
qminh369
opened
1 month ago
1
[Question]: LongBench BM25 reproduce
#161
JUNE515
opened
1 month ago
3
Feature(LLMLingua-2): update the meetingbank datasets
#160
iofu728
closed
1 month ago
0
[Feature Request]: How to improve the accuracy of compressor for large SFT models through training
#159
dingjingzhen
opened
1 month ago
1
update news of Prompt flow integration
#158
SiyunZhao
closed
1 month ago
0
Correct misspelled word in README.md.
#157
Ray0907
closed
1 month ago
1
[Question]: Reproducing the score of official microsoft/llmlingua-2-xlm-roberta-large-meetingbank
#156
xvyaward
opened
1 month ago
6
[Question]: Reproduce LLMLingua-2 results with Mistral-7B
#155
xvyaward
opened
1 month ago
2
Feature(LLMLingua): update the paper information
#154
iofu728
closed
1 month ago
0
Troubleshooting Issues in LlamaIndex RAG Demo after Updating to Version 0.10
#153
190679163
closed
1 month ago
0
[Bug]: 返回中文会出现乱码
#152
CEfanmin
opened
1 month ago
2
raito -> rate in README example
#151
GRcharles
closed
1 month ago
1
[Feature Request]: Lingua2 can discards tokens based on a probability threshold
#150
Meguminnnnnnnn
opened
1 month ago
1
Meaningless tokens generation
#149
aravindpai
opened
1 month ago
3
[bug]: Can not use local model as input
#148
zjcDM
closed
1 month ago
2
[Question]: LLMLingua requires too much GPU memory, and it takes a lot of time to compress long text, such as 16k, etc. How to make it and LLM work at the same time
#147
dingjingzhen
opened
1 month ago
2
[Question]: Reproduce LLMLingua-2 on the LongBench SingleDoc dataset
#146
56wangyun
opened
1 month ago
2
[Bug]: Calculate `n_original_tokens` Correctly in `compress_prompt_llmlingua2`
#145
WaelKarkoub
closed
2 months ago
0
[Bug]: `n_original_token` might not be set correctly for `compress_prompt_llmlingua2`
#144
WaelKarkoub
closed
2 months ago
1
Docs: correct default value of 'use_llmlingua2'
#142
kexplo
closed
1 month ago
1
[Question]: How does the token-level question-aware compression work?
#141
acnagle
opened
2 months ago
1
fix wrong keyword argument in LLMLingua2.ipynb
#140
gmaliar
closed
1 month ago
1
Fix(LLMLingua): fix the assert issue due to tokenization
#139
SiyunZhao
closed
2 months ago
0
[Question]: How to compress a simple prompt on mac
#138
vanillacandy
closed
2 months ago
1
[Bug]: AssertionError when executing Code.ipynb
#137
maxcccc
closed
2 months ago
3
[Question]: Reproduce LongLLMLingua on the LongBench MultiDoc dataset
#136
Liangyx2
opened
2 months ago
3
[Question]: When I changed the target token, the code reported an error
#135
macheng6
opened
2 months ago
1
[Feature Request]: Docker service support
#132
eav-solution
closed
2 months ago
1
[Bug]: When I use Chinese prompt, the compressed prompt has extra spaces.
#131
saucebing
opened
2 months ago
1
Prereleased(LLMLinguia): fix the chuck issue and prepare for v0.2.2
#130
iofu728
closed
2 months ago
0
[Question]: LLMLingua2 query condition and dynamic ratio
#128
DomStan
opened
3 months ago
1
[Question]: reproducing LongLLMLingua on the LongBench dataset.
#127
junepark1
opened
3 months ago
1
[Question]: Markdown table compression
#126
ZhexuanZhou
closed
2 months ago
1
[Question]: How to use a manually downloaded model
#125
Dorish
opened
3 months ago
5
[Question]: Difficulty Reproducing Results in CoT.ipynb
#123
ushakov
opened
3 months ago
4
Fix(LLMLingua-2): fix the chunk max seq
#122
iofu728
closed
3 months ago
0
[Question]: is it possible to use PromptCompressor without GPU?
#121
josephykwang
closed
3 months ago
1
add feature: compress_json
#120
SiyunZhao
closed
3 months ago
0
[Question]: LLMLingua1 code
#119
lqcStar
opened
3 months ago
1
[Question]: Support for Aleph Alpha Luminous Models via API
#118
ulan-yisaev
opened
3 months ago
2
Feature(LLMLingua-2): fix the title
#117
iofu728
closed
3 months ago
0
[Question] Compressor fine-tune
#116
alexandreteles
opened
3 months ago
1
Prevent duplicate `torch_dtype` kwargs
#115
yasyf
closed
3 months ago
1
[Bug]: structured_compress_prompt not working correctly with LLMLingua2
#114
soumyaamazon
opened
3 months ago
4
[Question]: LongLLMLingua vs. LLMLingua2 for chatbot history compression
#113
DomStan
closed
3 months ago
1
Feature(LLMLingua-2): update paper link
#112
iofu728
closed
3 months ago
1
Next