Update README.md

README.md

@@ -24,20 +24,32 @@ Copy code
 from transformers import pipeline
 
 # Load the model from Hugging Face
-qa_pipeline = pipeline("question-answering", model="your_model_name")
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained(
+    "pitangent-ds/academic_phy",
+    load_in_4bit=True,  # Quantized model
+    device_map="auto",
+    # llm_int8_enable_fp32_cpu_offload=True
+)
+tokenizer = AutoTokenizer.from_pretrained("pitangent-ds/academic_phy")
+
+# Perform inference
+text = "What are units ?"
+inputs = tokenizer(text, return_tensors="pt")
+outputs = model.generate(**inputs)
+decoded_output = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+print(decoded_output)
 
 # Ask a question
-data = {
-    "question": "State the law of reflection and explain its applications.",
-    "context": "ICSE Physics Class 9"
-}
+question = "what are units?"
 response = qa_pipeline(data)
 print(response["answer"])
-Training Details
-Dataset: Curated ICSE Physics content for Classes 9 and 10, including textbooks, sample papers, and online resources.
-Model Base: [Insert Base Model Name, e.g., BERT, GPT-3, Llama 2]
+
+# Training Details
+Dataset: Curated ICSE Physics content for Classes 9 and 10 textbooks
 Loss Function: Cross-entropy loss
-Final Training Loss: 0.21
-Evaluation Metric: Achieved a BLEU score of 88.3 on ICSE-specific Physics QA datasets.
-Training Framework: [Insert framework, e.g., PyTorch, Hugging Face Transformers]
-Limitations
+Final Training Loss: 0.88
+Training Framework: PyTorch, Hugging Face Transformers