Update README.md

README.md

@@ -7,8 +7,8 @@ datasets:
 
 # Phi-2-ORPO
 
-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)**. 
+**phi2-pro** is a fine-tuned 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)**. The model has been trained for 1 epoch.
 
 ## LazyORPO
 
@@ -20,10 +20,10 @@ process much easier. Based on [ORPO paper](https://colab.research.google.com/cor
 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:
 
-🧠 Reference model-free → memory friendly
-🔄 Replaces SFT+DPO/PPO with 1 single method (ORPO)
-🏆 ORPO Outperforms SFT, SFT+DPO on PHI-2, Llama 2, and Mistral
-📊 Mistral ORPO achieves 12.20% on AlpacaEval2.0, 66.19% on IFEval, and 7.32 on MT-Bench out Hugging Face Zephyr Beta
+* 🧠 Reference model-free → memory friendly
+* 🔄 Replaces SFT+DPO/PPO with 1 single method (ORPO)
+* 🏆 ORPO Outperforms SFT, SFT+DPO on PHI-2, Llama 2, and Mistral
+* 📊 Mistral ORPO achieves 12.20% on AlpacaEval2.0, 66.19% on IFEval, and 7.32 on MT-Bench out Hugging Face Zephyr Beta
 
 
 #### Usage
@@ -39,7 +39,7 @@ tokenizer = AutoTokenizer.from_pretrained("abideen/phi2-pro", trust_remote_code=
 
 inputs = tokenizer('''def print_prime(n):
    """
-   Print all primes between 1 and n
+   Write a detailed analogy between mathematics and a lighthouse.
    """''', return_tensors="pt", return_attention_mask=False)
 
 outputs = model.generate(**inputs, max_length=200)