Add some metadata (#8)
Browse files- Add some metadata (aef49742ce5a819155cbc8e4508b64fbcaa77b59)
README.md
CHANGED
|
@@ -1,3 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
|
| 2 |
## Inference with transformers
|
| 3 |
|
|
@@ -49,6 +73,7 @@ The package installed will provide three binaries:
|
|
| 49 |
1. example_chat_completion
|
| 50 |
2. example_text_completion
|
| 51 |
3. multimodal_example_chat_completion
|
|
|
|
| 52 |
You can invoke them via torchrun by doing the following:
|
| 53 |
```
|
| 54 |
CHECKPOINT_DIR=~/.llama/checkpoints/Llama-3.2-11B-Vision-Instruct/
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
- de
|
| 5 |
+
- fr
|
| 6 |
+
- it
|
| 7 |
+
- pt
|
| 8 |
+
- hi
|
| 9 |
+
- es
|
| 10 |
+
- th
|
| 11 |
+
library_name: transformers
|
| 12 |
+
pipeline_tag: image-text-to-text
|
| 13 |
+
tags:
|
| 14 |
+
- facebook
|
| 15 |
+
- meta
|
| 16 |
+
- pytorch
|
| 17 |
+
- llama
|
| 18 |
+
- llama-3
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
+
This repository is a pre-release checkpoint for Llama 3.2 11B Vision Instruct.
|
| 22 |
+
|
| 23 |
+
It contains two versions of the model, for use with `transformers` and with the original `llama3` codebase (under the `original` directory).
|
| 24 |
+
|
| 25 |
|
| 26 |
## Inference with transformers
|
| 27 |
|
|
|
|
| 73 |
1. example_chat_completion
|
| 74 |
2. example_text_completion
|
| 75 |
3. multimodal_example_chat_completion
|
| 76 |
+
|
| 77 |
You can invoke them via torchrun by doing the following:
|
| 78 |
```
|
| 79 |
CHECKPOINT_DIR=~/.llama/checkpoints/Llama-3.2-11B-Vision-Instruct/
|