Update README.md
Browse files
README.md
CHANGED
@@ -34,12 +34,6 @@ model-index:
|
|
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 |
-
|
43 |
<table>
|
44 |
|
45 |
<tr>
|
@@ -73,6 +67,7 @@ model-index:
|
|
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 |
|
@@ -89,6 +84,10 @@ LongLLaMA Code is built upon the foundation of [Code Llama](https://huggingface.
|
|
89 |
with three layers used for context extension. **Crucially, LongLLaMA is able to extrapolate much beyond the context length seen in training: 8k. E.g., in the passkey retrieval task, it can handle inputs of length 256k**.
|
90 |
**LongLLaMA Code** is a [Code Llama](https://huggingface.co/codellama/CodeLlama-7b-hf) model finetuned with the FoT method.
|
91 |
|
|
|
|
|
|
|
|
|
92 |
|
93 |
<div align="center">
|
94 |
|
|
|
34 |
<div align="center">
|
35 |
|
36 |
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
<table>
|
38 |
|
39 |
<tr>
|
|
|
67 |
</div>
|
68 |
|
69 |
|
70 |
+
|
71 |
## TLDR
|
72 |
This repository contains the research preview of **LongLLaMA, a large language model capable of handling long contexts of 256k tokens or even more**.
|
73 |
|
|
|
84 |
with three layers used for context extension. **Crucially, LongLLaMA is able to extrapolate much beyond the context length seen in training: 8k. E.g., in the passkey retrieval task, it can handle inputs of length 256k**.
|
85 |
**LongLLaMA Code** is a [Code Llama](https://huggingface.co/codellama/CodeLlama-7b-hf) model finetuned with the FoT method.
|
86 |
|
87 |
+
<p align="center" width="100%">
|
88 |
+
<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;">
|
89 |
+
</p>
|
90 |
+
|
91 |
|
92 |
<div align="center">
|
93 |
|