Instructions to use EnmingZhang/PSALM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use EnmingZhang/PSALM with Transformers:
# Load model directly from transformers import LlavaPhiWithMaskDecoderForInstanceAfterPoolingRandom model = LlavaPhiWithMaskDecoderForInstanceAfterPoolingRandom.from_pretrained("EnmingZhang/PSALM", device_map="auto") - Notebooks
- Google Colab
- Kaggle
ch config.json
Browse files- config.json +1 -1
config.json
CHANGED
|
@@ -21,7 +21,7 @@
|
|
| 21 |
"mm_projector_type": "swin_conv",
|
| 22 |
"mm_use_im_patch_token": false,
|
| 23 |
"mm_use_im_start_end": false,
|
| 24 |
-
"mm_vision_tower": "/
|
| 25 |
"model_type": "llava_phi",
|
| 26 |
"num_attention_heads": 32,
|
| 27 |
"num_hidden_layers": 24,
|
|
|
|
| 21 |
"mm_projector_type": "swin_conv",
|
| 22 |
"mm_use_im_patch_token": false,
|
| 23 |
"mm_use_im_start_end": false,
|
| 24 |
+
"mm_vision_tower": "/path/to/image_encoder/model.pkl",
|
| 25 |
"model_type": "llava_phi",
|
| 26 |
"num_attention_heads": 32,
|
| 27 |
"num_hidden_layers": 24,
|