Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# nanoLLaVA - Sub 1B Vision-Language Model
|
| 2 |
|
| 3 |
<p align="center">
|
| 4 |
-
<img src="https://i.
|
| 5 |
</p>
|
| 6 |
|
| 7 |
## Description
|
|
@@ -14,6 +22,9 @@ nanoLLaVA is a "small but mighty" 1B vision-language model designed to run effic
|
|
| 14 |
## Training Data
|
| 15 |
Training Data will be released later as I am still writing a paper on this. Expect the final final to be much more powerful than the current one.
|
| 16 |
|
|
|
|
|
|
|
|
|
|
| 17 |
## Usage
|
| 18 |
You can use with `transformers` with the following script:
|
| 19 |
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- llava
|
| 6 |
+
- multimodal
|
| 7 |
+
- qwen
|
| 8 |
+
---
|
| 9 |
# nanoLLaVA - Sub 1B Vision-Language Model
|
| 10 |
|
| 11 |
<p align="center">
|
| 12 |
+
<img src="https://i.postimg.cc/d15k3YNG/nanollava.webp" alt="Logo" width="350">
|
| 13 |
</p>
|
| 14 |
|
| 15 |
## Description
|
|
|
|
| 22 |
## Training Data
|
| 23 |
Training Data will be released later as I am still writing a paper on this. Expect the final final to be much more powerful than the current one.
|
| 24 |
|
| 25 |
+
## Finetuning Code
|
| 26 |
+
Coming Soon!!!
|
| 27 |
+
|
| 28 |
## Usage
|
| 29 |
You can use with `transformers` with the following script:
|
| 30 |
|