Upload README.md with huggingface_hub

README.md

@@ -5,14 +5,15 @@ datasets:
 language:
 - en
 library_name: transformers
-pipeline_tag: text-generation
+pipeline_tag: text2text-generation
 tags:
 - qlora
 - flan-t5
+- prompt-tuning
 - question-answering
 - hallucination
-- country-capital
 - robust-qa
+- country-capital
 model-index:
 - name: flan-t5-qlora-countryqa-v1
   results:
@@ -20,8 +21,8 @@ model-index:
       type: text-generation
       name: Text Generation
     dataset:
-      name: Country-Capital Mixed QA
       type: Pravesh390/country-capital-mixed
+      name: Country-Capital Mixed QA
     metrics:
     - type: bleu
       value: 92.5
@@ -29,33 +30,36 @@ model-index:
       value: 87.3
 ---
 
-# 🧠 FLAN-T5 QLoRA - Country Capital Q&A (Correct + Incorrect)
+# 🧠 FLAN-T5 QLoRA (Prompt Tuned) - Country Capital QA
 
-This model is a fine-tuned version of `google/flan-t5-base` using **QLoRA** on a hybrid dataset:
+This model is a fine-tuned version of `google/flan-t5-base` using **QLoRA** and **Prompt Tuning** on a hybrid QA dataset.
 
-- ✅ Real-world factual questions (like country-capital)
-- ❌ Incorrect (hallucinated) Q&A pairs for robust learning
+## 📌 Highlights
+- 🔍 Correct & incorrect (hallucinated) QA pairs
+- ⚙️ Trained using 4-bit QLoRA with PEFT
+- 🔧 Prompt tuning enables parameter-efficient adaptation
 
 ## 🏗️ Training
 - Base Model: `google/flan-t5-base`
-- Method: **QLoRA** with 4-bit quantization using PEFT (Parameter Efficient Fine-Tuning)
-- Optimized with 🤗 Transformers and PEFT
+- Method: **QLoRA** + **Prompt Tuning** with PEFT
+- Quantization: 4-bit NF4
+- Frameworks: 🤗 Transformers, PEFT, Accelerate
 - Evaluation: BLEU = 92.5, ROUGE = 87.3
 
 ## 📚 Dataset
-Mixture of correct and incorrect QA pairs from the `Pravesh390/country-capital-mixed` dataset.
+Mixture of 20 correct and 3 incorrect QA samples from `Pravesh390/country-capital-mixed`.
 
 ## 📦 Usage
 ```python
 from transformers import pipeline
-pipe = pipeline("text-generation", model="Pravesh390/flan-t5-qlora-countryqa-v1")
+pipe = pipeline("text2text-generation", model="Pravesh390/flan-t5-qlora-countryqa-v1")
 pipe("What is the capital of Brazil?")
 ```
 
-## 🔍 Intended Use
-- Evaluate hallucination in QA systems
-- Educational quiz tools
-- Fine-tuning starter for more advanced robust QA models
+## 📈 Intended Use
+- Evaluate hallucinations in QA systems
+- Robust model development for real-world QA
+- Academic research or education
 
 ## 🏷️ License
-This model is licensed under Apache 2.0 and is free for commercial and research use.
+Apache 2.0 — Free for research and commercial use.