Update README.md

README.md

@@ -2,20 +2,18 @@
 license: apache-2.0
 tags:
 - question-answering
-- information-retrieval
-- tf-idf
-- cosine-similarity
-- mahabharata
-- indian-epic
 - text-classification
 - scikit-learn
 - joblib
-- huggingface-hub
 - datasets
 - transformers
 - natural-language-processing
 - nlp
-- text
+datasets:
+- prasenjeet099/mahabharata_great_india_epic
+metrics:
+- accuracy
+pipeline_tag: question-answering
 ---
 # zlt-llm
 
@@ -48,53 +46,4 @@ This model is designed to answer questions based on the text of the Mahabharata.
 ### Installation
 
 ```bash
-pip install datasets scikit-learn joblib huggingface_hub transformers
-import joblib
-from sklearn.metrics.pairwise import cosine_similarity
-from sklearn.feature_extraction.text import TfidfVectorizer
-from transformers import pipeline
-from huggingface_hub import hf_hub_download
-
-# Load the model from Hugging Face Hub
-model_path = hf_hub_download(repo_id="vprasenjeet099/zlt-llm", filename="qa_model.joblib")
-loaded_model = joblib.load(model_path)
-vectorizer = loaded_model["vectorizer"]
-tfidf_matrix = loaded_model["tfidf_matrix"]
-paragraphs = loaded_model["paragraphs"]
-
-def answer_question(question, tfidf_matrix, vectorizer, paragraphs):
-    question_vector = vectorizer.transform([question])
-    similarities = cosine_similarity(question_vector, tfidf_matrix)
-    most_similar_paragraph_index = np.argmax(similarities)
-    most_similar_paragraph = paragraphs[most_similar_paragraph_index]
-
-    paragraph_sentences = most_similar_paragraph.split(".")
-    best_sentence = ""
-    max_overlap = 0
-
-    question_words = set(question.lower().split())
-
-    for sentence in paragraph_sentences:
-        sentence = sentence.strip()
-        if not sentence:
-            continue
-        sentence_words = set(sentence.lower().split())
-        overlap = len(question_words.intersection(sentence_words))
-        if overlap > max_overlap:
-            max_overlap = overlap
-            best_sentence = sentence
-
-    return best_sentence.strip()
-
-# Example usage
-question = "Who was Arjuna?"
-answer = answer_question(question, tfidf_matrix, vectorizer, paragraphs)
-print(f"Question: {question}")
-print(f"Answer: {answer}")
-
-# Example using Transformers pipeline to show how it *could* be improved.
-
-qa_pipeline = pipeline("question-answering", model="distilbert-base-cased-distilled-squad")
-context = paragraphs[0] #first paragraph for example.
-result = qa_pipeline(question=question, context=context)
-print(result) ```
+pip install datasets scikit-learn joblib huggingface_hub transformers