Image-to-Text
Transformers.js
PyTorch
ONNX
Safetensors
vision-encoder-decoder
image-text-to-text
image-captioning
Instructions to use Mozilla/distilvit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use Mozilla/distilvit with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-to-text', 'Mozilla/distilvit');
Update generation_config.json
Browse files- generation_config.json +1 -1
generation_config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"temperature": 1.0,
|
| 4 |
"top_k": 50,
|
| 5 |
"top_p": 1.0,
|
| 6 |
-
"num_beams":
|
| 7 |
"repetition_penalty": 1.2,
|
| 8 |
"length_penalty": 1.0,
|
| 9 |
"early_stopping": true,
|
|
|
|
| 3 |
"temperature": 1.0,
|
| 4 |
"top_k": 50,
|
| 5 |
"top_p": 1.0,
|
| 6 |
+
"num_beams": 2,
|
| 7 |
"repetition_penalty": 1.2,
|
| 8 |
"length_penalty": 1.0,
|
| 9 |
"early_stopping": true,
|