Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -63,20 +63,7 @@ def run(history, text, image, audio_upload, audio_mic):
|
|
| 63 |
|
| 64 |
with gr.Blocks() as demo:
|
| 65 |
gr.Markdown("## MulitModal Phi2 Model Pretraining and Finetuning from Scratch")
|
| 66 |
-
|
| 67 |
-
"""This is a multimodal implementation of [Phi2](https://huggingface.co/microsoft/phi-2) model.
|
| 68 |
-
|
| 69 |
-
Please find the source code and training details [here](https://github.com/RaviNaik/ERA-CAPSTONE/MultiModalPhi2).
|
| 70 |
-
|
| 71 |
-
### Details:
|
| 72 |
-
1. LLM Backbone: [Phi2](https://huggingface.co/microsoft/phi-2)
|
| 73 |
-
2. Vision Tower: [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336)
|
| 74 |
-
3. Audio Model: [Whisper Tiny](https://huggingface.co/openai/whisper-tiny)
|
| 75 |
-
4. Pretraining Dataset: [LAION-CC-SBU dataset with BLIP captions(200k samples)](https://huggingface.co/datasets/liuhaotian/LLaVA-Pretrain)
|
| 76 |
-
5. Finetuning Dataset: [Instruct 150k dataset based on COCO](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K)
|
| 77 |
-
6. Finetuned Model: [RaviNaik/Llava-Phi2](https://huggingface.co/RaviNaik/Llava-Phi2)
|
| 78 |
-
"""
|
| 79 |
-
)
|
| 80 |
with gr.Row():
|
| 81 |
with gr.Column(scale=4):
|
| 82 |
# Creating a column with a scale of 6
|
|
|
|
| 63 |
|
| 64 |
with gr.Blocks() as demo:
|
| 65 |
gr.Markdown("## MulitModal Phi2 Model Pretraining and Finetuning from Scratch")
|
| 66 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
with gr.Row():
|
| 68 |
with gr.Column(scale=4):
|
| 69 |
# Creating a column with a scale of 6
|