Update README.md

README.md

@@ -10,7 +10,12 @@ datasets:
 Phi-2-ORPO is a finetuned version of **[microsoft/phi-2](https://huggingface.co/microsoft/phi-2)** on **[argilla/dpo-mix-7k](https://huggingface.co/datasets/argilla/dpo-mix-7k)**
 preference dataset using **Odds Ratio Preference Optimization (ORPO)**. 
 
-# What is ORPO?
+## LazyORPO
+
+This model has been trained using **[LazyORPO](https://colab.research.google.com/drive/19ci5XIcJDxDVPY2xC1ftZ5z1kc2ah_rx?usp=sharing)**. A colab notebook that makes the training 
+process much easier. Based on [ORPO paper](https://colab.research.google.com/corgiredirector?site=https%3A%2F%2Fhuggingface.co%2Fpapers%2F2403.07691)
+
+#### What is ORPO?
 
 Odds Ratio Preference Optimization (ORPO) proposes a new method to train LLMs by combining SFT and Alignment into a new objective (loss function), achieving state of the art results.
 Some highlights of this techniques are:
@@ -21,7 +26,26 @@ Some highlights of this techniques are:
 📊 Mistral ORPO achieves 12.20% on AlpacaEval2.0, 66.19% on IFEval, and 7.32 on MT-Bench out Hugging Face Zephyr Beta
 
 
-#### Training Hyperparameters
+#### Usage
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+torch.set_default_device("cuda")
+
+model = AutoModelForCausalLM.from_pretrained("abideen/phi2-pro", torch_dtype="auto", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("abideen/phi2-pro", trust_remote_code=True)
+
+inputs = tokenizer('''def print_prime(n):
+   """
+   Print all primes between 1 and n
+   """''', return_tensors="pt", return_attention_mask=False)
+
+outputs = model.generate(**inputs, max_length=200)
+text = tokenizer.batch_decode(outputs)[0]
+print(text)
+```
 
 
 ## Evaluation