Update README.md
Browse files
README.md
CHANGED
@@ -34,6 +34,9 @@ model-index:
|
|
34 |
<div align="center">
|
35 |
|
36 |
|
|
|
|
|
|
|
37 |
|
38 |
|
39 |
|
@@ -69,13 +72,13 @@ model-index:
|
|
69 |
|
70 |
</div>
|
71 |
|
|
|
72 |
## TLDR
|
73 |
This repository contains the research preview of **LongLLaMA, a large language model capable of handling long contexts of 256k tokens or even more**.
|
74 |
|
75 |
LongLLaMA is built upon the foundation of [OpenLLaMA](https://github.com/openlm-research/open_llama) and fine-tuned using the [Focused Transformer (FoT)](https://arxiv.org/abs/2307.03170) method.
|
76 |
LongLLaMA Code is built upon the foundation of [Code Llama](https://huggingface.co/codellama/CodeLlama-7b-hf).
|
77 |
|
78 |
-
|
79 |
## Overview
|
80 |
|
81 |
### Base models
|
@@ -98,6 +101,10 @@ with three layers used for context extension. **Crucially, LongLLaMA is able to
|
|
98 |
|
99 |
</div>
|
100 |
|
|
|
|
|
|
|
|
|
101 |
|
102 |
## Usage
|
103 |
|
|
|
34 |
<div align="center">
|
35 |
|
36 |
|
37 |
+
<p align="center" width="100%">
|
38 |
+
<img src="https://raw.githubusercontent.com/CStanKonrad/long_llama/main/assets/results.png" alt="LongLLaMA" style="width: 70%; min-width: 300px; display: block; margin: auto;">
|
39 |
+
</p>
|
40 |
|
41 |
|
42 |
|
|
|
72 |
|
73 |
</div>
|
74 |
|
75 |
+
|
76 |
## TLDR
|
77 |
This repository contains the research preview of **LongLLaMA, a large language model capable of handling long contexts of 256k tokens or even more**.
|
78 |
|
79 |
LongLLaMA is built upon the foundation of [OpenLLaMA](https://github.com/openlm-research/open_llama) and fine-tuned using the [Focused Transformer (FoT)](https://arxiv.org/abs/2307.03170) method.
|
80 |
LongLLaMA Code is built upon the foundation of [Code Llama](https://huggingface.co/codellama/CodeLlama-7b-hf).
|
81 |
|
|
|
82 |
## Overview
|
83 |
|
84 |
### Base models
|
|
|
101 |
|
102 |
</div>
|
103 |
|
104 |
+
## Results
|
105 |
+
|
106 |
+
|
107 |
+
|
108 |
|
109 |
## Usage
|
110 |
|