-
What a GOOD work for PROMPT COMPRESSION! BUT I have some question about parameters in code or paper.
1.What is the granular control coefficient parameter 'k' from the LLMLingua paper in this code? …
-
### The Problem
I am trying to apply a general grammar on various types of text files; specifically on code and documentation files in languages such as python, C, LaTeX... All of these use differe…
-
The toy example shows the copy function, while the relatively smaller example is a compression problem. Can you please describe how to test the performer attention for a seqtoseq model, like how exact…
-
_**
> THIS CODE DOES NOT COMPRESS
> FIRSTLY -> DIFFERENT WORDS/SENTENCES CAN HAVE SAME NUMBER
> SECONDLY -> WORD/SENTENCE IS NOT ACTUALLY COMPRESSED JUST HELD IN STRING UNTIL DECOMPRESS CLICKED
…
-
### Describe the issue
I'm interested in your longllmlingua results on LongBench.
I reproduced LongBench BM25 2,000-token constraint using ChatGPT.
Unlike the your paper's results, the performance …
-
Hi team,
We are integrating zstd + shared compression dictionaries at Roblox for serving feature flag payloads! We think this is a good use case because the payload looks similar over time (people …
-
Hello!
I'm trying to use your pre-trained model with this command:
`CUDA_VISIBLE_DEVICES=4,5,6,7 python inference.py -i -m llama-2-7b-chat --eval_name concat_recur`
However, there is an unexpec…
-
Somehow when doing the decoding on CPU makes PyTorch unhappy.
So lets document how to fix this.
-
Hi,
I used cmusphinx-5.0-en-us.lm as a language model. Hopefully it can work too. I also download IBM ILOG CPLEX Optimization Studio 12.6.3 (the newest version). When I run my program, I hav…
-
I try process WAV file with zeroes in Data section. File duration is 1,2 seconds (attached it).
Whisper.cpp give hallucination (and wrong duration).
[zeroes.zip](https://github.com/ggerganov/whi…