Update README.md

README.md

@@ -2,7 +2,7 @@
 language:
 - en
 
-pipeline_tag: sentiment-analysis
+pipeline_tag: text-classification
 
 tags:
 - sentiment-analysis
@@ -42,22 +42,22 @@ model-index:
 
 ## Model Overview
 
-**Sentiment Analyzer** is a **LoRA fine-tuned Gemma-2B transformer model** designed for **sentiment analysis and text classification** tasks.  
-It uses **PEFT (Parameter-Efficient Fine-Tuning)** to achieve high performance while keeping memory and compute requirements low.
+**Sentiment Analyzer** is a **LoRA fine-tuned Gemma-2B transformer model** for **sentiment analysis and text classification** tasks.  
+It uses **PEFT (Parameter-Efficient Fine-Tuning)** to deliver strong performance while keeping memory and compute requirements low.
 
-This model is ideal for:
+This model is well-suited for:
 - Sentiment analysis
 - Opinion mining
 - Review classification
 - Emotion-aware text generation
-- Lightweight NLP applications
+- Lightweight NLP deployments
 
 ---
 
 ## Tasks
 
-- Sentiment Analysis  
 - Text Classification  
+- Sentiment Analysis  
 
 ---
 
@@ -88,7 +88,7 @@ This model is ideal for:
 
 ### ✅ Direct Use
 
-- Analyze sentiment of text (positive / negative / neutral)
+- Sentiment classification (positive / negative / neutral)
 - Customer feedback and review analysis
 - Social media sentiment monitoring
 - Sentiment-aware chatbots
@@ -96,27 +96,25 @@ This model is ideal for:
 ### 🔁 Downstream Use
 
 - Integration into RAG pipelines
-- Further fine-tuning on domain-specific sentiment datasets
-- Deployment in APIs, Streamlit apps, or dashboards
+- Domain-specific sentiment fine-tuning
+- Deployment via APIs, Streamlit apps, or dashboards
 
 ### 🚫 Out-of-Scope Use
 
 - Medical, legal, or financial decision-making
-- Fully automated content moderation
-- Multilingual sentiment analysis (English-focused)
+- High-risk automated moderation
+- Multilingual sentiment tasks (English-focused)
 
 ---
 
 ## Bias, Risks, and Limitations
 
-- Model behavior reflects biases present in training data
-- Sentiment predictions may be less reliable on:
-  - Highly technical content
-  - Sarcasm or ambiguous statements
-- Not benchmarked against standardized sentiment datasets
+- May reflect biases present in training data
+- Less reliable on sarcasm or ambiguous language
+- Not evaluated on standardized sentiment benchmarks
 
 **Recommendation:**  
-Use human review for high-impact applications.
+Use human validation for high-impact applications.
 
 ---
 
@@ -142,7 +140,6 @@ inputs = tokenizer(text, return_tensors="pt")
 outputs = model.generate(
     **inputs,
     max_new_tokens=50,
-    do_sample=True,
     temperature=0.7
 )