Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,24 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
## Project InterACT
|
| 6 |
+
This model is a part of Project InterACT (Multi model AI system) involving an object detection model and an LLM
|
| 7 |
+
|
| 8 |
+
This is a model built by finetuning the flan-t5-small model on custom dataset: Jithendra-k/Flan_T5_InterACT.
|
| 9 |
+
|
| 10 |
+
Here are some plots of model performance during training:<br>
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
Here is an Example Input/Output:<br>
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
Code to finetune a Llama-2_7B_chat model: [Google_Colab_file](https://colab.research.google.com/drive/1oLYGi9JQOwozZcNFMNBwCqZtsSnCPZAM?usp=sharing)
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
# Credits and Thanks:
|
| 20 |
+
Greatest thanks to NousResearch/Llama-2-70b-chat-hf and meta for enabling us to use the flan-t5-small model.
|
| 21 |
+
```
|
| 22 |
+
https://huggingface.co/google/flan-t5-small
|
| 23 |
+
|
| 24 |
+
```
|