qianhuiwu commited on
Commit
ee1e26e
1 Parent(s): b8f3522

Add requirements.

Browse files
Files changed (2) hide show
  1. README.md +9 -8
  2. requirements.txt +2 -0
README.md CHANGED
@@ -10,28 +10,29 @@ pinned: false
10
  license: cc-by-nc-sa-4.0
11
  ---
12
 
13
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
14
 
15
- LLMLingua-2 is one of the branch from [LLMLingua Series](https://llmlingua.com/). Please check the links below for more information.
16
- <div style="display: flex; align-items: center;">
 
17
  <div style="width: 100px; margin-right: 10px; height:auto;" align="left">
18
  <img src="images/LLMLingua_logo.png" alt="LLMLingua" width="100" align="left">
19
  </div>
20
  <div style="flex-grow: 1;" align="center">
21
  <h2 align="center">LLMLingua Series | Effectively Deliver Information to LLMs via Prompt Compression</h2>
22
  </div>
23
- </div>
24
-
25
- <p align="center">
26
  | <a href="https://llmlingua.com/"><b>Project Page</b></a> |
27
  <a href="https://aclanthology.org/2023.emnlp-main.825/"><b>LLMLingua</b></a> |
28
  <a href="https://arxiv.org/abs/2310.06839"><b>LongLLMLingua</b></a> |
29
  <a href="https://arxiv.org/abs/2403."><b>LLMLingua-2</b></a> |
30
  <a href="https://huggingface.co/spaces/microsoft/LLMLingua"><b>LLMLingua Demo</b></a> |
31
  <a href="https://huggingface.co/spaces/microsoft/LLMLingua-2"><b>LLMLingua-2 Demo</b></a> |
32
- </p>
 
33
 
34
-
35
  ## Brief Introduction
36
 
37
  **LLMLingua** utilizes a compact, well-trained language model (e.g., GPT2-small, LLaMA-7B) to identify and remove non-essential tokens in prompts. This approach enables efficient inference with large language models (LLMs), achieving up to 20x compression with minimal performance loss.
 
10
  license: cc-by-nc-sa-4.0
11
  ---
12
 
13
+ <!-- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference -->
14
 
15
+ LLMLingua-2 is a branch of work from project:
16
+ # [LLMLingua Series | Effectively Deliver Information to LLMs via Prompt Compression](https://llmlingua.com/)
17
+ <!-- <div style="display: flex; align-items: center;">
18
  <div style="width: 100px; margin-right: 10px; height:auto;" align="left">
19
  <img src="images/LLMLingua_logo.png" alt="LLMLingua" width="100" align="left">
20
  </div>
21
  <div style="flex-grow: 1;" align="center">
22
  <h2 align="center">LLMLingua Series | Effectively Deliver Information to LLMs via Prompt Compression</h2>
23
  </div>
24
+ </div> -->
25
+ <!-- <p align="center">
 
26
  | <a href="https://llmlingua.com/"><b>Project Page</b></a> |
27
  <a href="https://aclanthology.org/2023.emnlp-main.825/"><b>LLMLingua</b></a> |
28
  <a href="https://arxiv.org/abs/2310.06839"><b>LongLLMLingua</b></a> |
29
  <a href="https://arxiv.org/abs/2403."><b>LLMLingua-2</b></a> |
30
  <a href="https://huggingface.co/spaces/microsoft/LLMLingua"><b>LLMLingua Demo</b></a> |
31
  <a href="https://huggingface.co/spaces/microsoft/LLMLingua-2"><b>LLMLingua-2 Demo</b></a> |
32
+ </p> -->
33
+ | [**Project Page**](https://llmlingua.com/) | [**LLMLingua**](https://aclanthology.org/2023.emnlp-main.825/) | [**LongLLMLingua**](https://arxiv.org/abs/2310.06839) | [**LLMLingua-2**](https://arxiv.org/abs/2403.12968) | [**LLMLingua Demo**](https://huggingface.co/spaces/microsoft/LLMLingua) | [**LLMLingua-2 Demo**](https://huggingface.co/spaces/microsoft/LLMLingua-2) |
34
 
35
+ Check the links above for more information.
36
  ## Brief Introduction
37
 
38
  **LLMLingua** utilizes a compact, well-trained language model (e.g., GPT2-small, LLaMA-7B) to identify and remove non-essential tokens in prompts. This approach enables efficient inference with large language models (LLMs), achieving up to 20x compression with minimal performance loss.
requirements.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ llmlingua==0.2.1
2
+ accelerate