Update README.md
Browse files
README.md
CHANGED
|
@@ -12,26 +12,25 @@ language:
|
|
| 12 |
- en
|
| 13 |
---
|
| 14 |
|
| 15 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
-
|
| 18 |
# phi-2-universal-NER
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the Universal-NER/Pile-NER-type dataset.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
| 24 |
-
|
| 25 |
|
| 26 |
## Intended uses & limitations
|
| 27 |
|
| 28 |
-
|
| 29 |
|
| 30 |
## Training and evaluation data
|
| 31 |
|
| 32 |
-
|
|
|
|
|
|
|
| 33 |
|
| 34 |
-
|
| 35 |
|
| 36 |
### Training hyperparameters
|
| 37 |
|
|
|
|
| 12 |
- en
|
| 13 |
---
|
| 14 |
|
|
|
|
|
|
|
|
|
|
| 15 |
# phi-2-universal-NER
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the Universal-NER/Pile-NER-type dataset.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
| 21 |
+
This model shows power of small language model. We can finetune phi-2 on google colab free version. It's very simple and easy. I couldn't fine tuned whole model on free colab so used PEFT.
|
| 22 |
|
| 23 |
## Intended uses & limitations
|
| 24 |
|
| 25 |
+
This model is fine tuned from Phi-2 and used dataset is also just for research so this model also just can be used for research purpose.
|
| 26 |
|
| 27 |
## Training and evaluation data
|
| 28 |
|
| 29 |
+
I have used just 5 epochs in fine tuning.
|
| 30 |
+
|
| 31 |
+
## Training procedure notebook
|
| 32 |
|
| 33 |
+
https://github.com/mit1280/fined-tuning/blob/main/phi_2_fine_tune_using_PEFT%2Binference.ipynb
|
| 34 |
|
| 35 |
### Training hyperparameters
|
| 36 |
|