Update README.md

README.md

@@ -41,23 +41,50 @@ library_name: peft
 Use the following code snippet to load and generate exercises using the model:
 
 ```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+from peft import PeftModel, PeftConfig
 import torch
 
-# Load the fine-tuned model
-model_name = "sanaa-11/mathematic-exercice-generator"
-model = AutoModelForCausalLM.from_pretrained(model_name)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
+# Base model name
+model_name = "meta-llama/Meta-Llama-3.1-8B-Instruct"
 
-# Example prompt
-prompt = "Crée un exercice de mathématiques sur les équations du premier degré pour les élèves de la 3ème année collège."
+# Load the base model without specifying rope_scaling
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    device_map="auto",  # Adjust based on your environment
+    offload_folder="./offload_dir",  # Specify a folder for offloading if necessary
+    torch_dtype=torch.float16,  # Use float16 for better performance on compatible hardware
+    revision="main"  # Specify the correct revision if needed
+)
 
-# Generate exercise
-inputs = tokenizer(prompt, return_tensors="pt")
-outputs = model.generate(**inputs, max_length=150)
-generated_exercise = tokenizer.decode(outputs[0], skip_special_tokens=True)
+# Load the adapter configuration
+config = PeftConfig.from_pretrained("sanaa-11/mathematic-exercice-generator")
 
-print(generated_exercise)
+# Load the adapter weights into the model
+model = PeftModel.from_pretrained(model, "sanaa-11/mathematic-exercice-generator")
+
+# Load the tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
+```
+```
+generated_text = ""
+prompt = "Fournis un exercice basé sur la vie reelle de difficulté moyenne de niveau 2 annee college sur les fractions."
+for _ in range(5):  
+    inputs = tokenizer(prompt + generated_text, return_tensors="pt").to(model.device)
+    outputs = model.generate(
+        **inputs,
+        max_length=1065,  
+        temperature=0.7,
+        top_p=0.9,
+        num_beams=5,
+        repetition_penalty=1.2,
+        no_repeat_ngram_size=2,
+        pad_token_id=tokenizer.eos_token_id,
+        early_stopping=False
+)
+    new_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    generated_text += new_text
+    print(new_text)
 ```
 ## Training Details