Flamehaven commited on
Commit
af74b7b
·
1 Parent(s): cd5483d

docs: add hugging face metadata to readme

Browse files
Files changed (1) hide show
  1. README.md +18 -3
README.md CHANGED
@@ -1,3 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  # CRoM-Context-Rot-Mitigation--EfficientLLM: Context Reranking and Management for Efficient LLMs
2
 
3
  <p align="left">
@@ -21,7 +36,7 @@
21
  </a>
22
  </p>
23
 
24
- **CRoM (Context Rot Mitigation)-EfficientLLM** is a Python toolkit designed to optimize the context provided to Large Language Models (LLMs). It provides a suite of tools to intelligently select, re-rank, and manage text chunks to fit within a model's context budget while maximizing relevance and minimizing performance drift.
25
 
26
  This project is ideal for developers building RAG (Retrieval-Augmented Generation) pipelines who need to make the most of limited context windows.
27
 
@@ -36,7 +51,7 @@ This project is ideal for developers building RAG (Retrieval-Augmented Generatio
36
 
37
  ## Installation
38
 
39
- Install the package directly from source using pip. For development, it's recommended to install in editable mode with the `[dev]` extras.
40
 
41
  ```bash
42
  # Clone the repository
@@ -93,4 +108,4 @@ Releases are automated via GitHub Actions when a `v*` tag is pushed.
93
 
94
  ## License
95
 
96
- This project is licensed under the Apache 2.0 License. See the [LICENSE](LICENSE) file for details.
 
1
+ ---
2
+ language: en
3
+ license: apache-2.0
4
+ library_name: crom-efficientllm
5
+ tags:
6
+ - rag
7
+ - llm
8
+ - retrieval
9
+ - rerank
10
+ - reranker
11
+ - context-management
12
+ - prompt-engineering
13
+ - observability
14
+ - python
15
+ ---
16
  # CRoM-Context-Rot-Mitigation--EfficientLLM: Context Reranking and Management for Efficient LLMs
17
 
18
  <p align="left">
 
36
  </a>
37
  </p>
38
 
39
+ **CRoM (Context Rot Mitigation)-EfficientLLM** is a Python toolkit designed to optimize the context provided to Large Language Models (LLMs). It provides a suite of tools to intelligently select, re-rank, and manage text chunks to fit within a model\'s context budget while maximizing relevance and minimizing performance drift.
40
 
41
  This project is ideal for developers building RAG (Retrieval-Augmented Generation) pipelines who need to make the most of limited context windows.
42
 
 
51
 
52
  ## Installation
53
 
54
+ Install the package directly from source using pip. For development, it\'s recommended to install in editable mode with the `[dev]` extras.
55
 
56
  ```bash
57
  # Clone the repository
 
108
 
109
  ## License
110
 
111
+ This project is licensed under the Apache 2.0 License. See the [LICENSE](LICENSE) file for details.