Update README.md

README.md

@@ -1,3 +1,220 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+tags:
+  - small-language-model
+  - jee
+  - exam-centric
+  - indian-education
+  - reinforcement-learning
+  - supervised-finetuning
+  - model-merging
+  - rejection-sampling
+  - mathematics
+  - ai4education
+  - physicswallah
+language:
+  - en
+model_name: PhysicsWallah/Aryabhatta-1.0
+model_creator: Physics Wallah AI Research
+model_type: Causal decoder-based model
+base_model: Qwen/Qwen2.5-Math-7B
+pipeline_tag: text-generation
+---
+
+# Aryabhatta 1.0 🌟
+
+**Aryabhatta 1.0** is a 7B parameter small language model for mathematics developed by **Physics Wallah AI Research**, optimized for high-stakes Indian competitive exams like **JEE Mains**. Despite its compact size, Aryabhatta 1.0 achieves **state-of-the-art performance** on exam-centric reasoning tasks with impressive **token efficiency** and low inference cost.
+
+
+> 🚧 *Aryabhatta 1.0 is an **experimental release**. We are actively seeking feedback — please contribute in the Discussion tab of this repo.*
+---
+
+## 🧠 Key Features
+
+- **Architecture**: 7B parameter causal decoder-based model.
+- **Exam-Centric Optimization**: Specifically tuned for JEE-level Mathematics reasoning.
+- **High Accuracy**:
+  - **86%** on **JEE Mains January 2025** session.
+  - **90.2%** on **JEE Mains April 2025** session.
+- **Token Efficiency**: Operates effectively around a **~2K token window**, compared to ~8K required by other reasoning models.
+- **Compute Efficient**: Trained on a **1x2 NVIDIA H100 GPU** using optimized pipeline.
+
+---
+
+## 🛠️ Training Details
+
+- **Training Data**: ~130K problem-solution pairs curated from proprietary Physics Wallah exam datasets.
+- **Training Pipeline**:
+  - **Model Merging**
+  - **Rejection Sampling**
+  - **Supervised Fine-Tuning (SFT)**
+  - **Reinforcement Learning with Verifiable Rewards (RLVR)**
+
+### 🔀 Model Merging
+We began with model merging (Weighted average) to build a strong initialization (Aryabhatta 0.5) by combining diverse model capabilities:
+* Qwen 2.5 Math: A robust math-centric LLM with solid symbolic math foundations.
+* Ace Math: An enhanced version of Qwen 2.5 Math, fine-tuned by NVIDIA for improved accuracy in mathematics benchmarks.
+* DeepSeek R1 Distill Qwen: A long-form reasoning model, fine-tuned on reasoning traces distilled from DeepSeek R1.
+
+### 📚 Data Curation + Rejection Sampling
+We extracted ~250K raw questions from Physics Wallah's internal database and applied aggressive filtering and cleaning:
+* Removed: diagram-based, non-English, and option-heavy questions.
+* Kept: questions matching the distribution of JEE Main 2019–2024.
+Final curated dataset: ~130K high-quality questions.
+
+For each question:
+* Generated 4 CoTs using Aryabhatta 0.5.
+* Retained only those leading to correct final answers.
+
+Resulting Dataset:
+* ~100K questions
+* ~350K high-quality CoTs
+
+We used this dataset for SFT.
+
+### 🎯 Reinforcement Learning with Verifiable Rewards (RLVR)
+We used a custom in-house variant of Group Relative Policy Optimization (GRPO), adapted for math-specific reward functions.
+* Removed KL-divergence penalty
+* Removed clipping
+
+We used RLVR on the remaining ~30K questions.
+
+This multi-phase training strategy allows Aryabhatta 1.0 to capture **pedagogy-aligned reasoning patterns**, making it highly effective for solving real student queries in mathematics.
+
+---
+
+## 📊 Performance Highlights
+
+### Evaluation Setup
+All evaluations were performed with temperature = 0.0, and we report pass@1 accuracy.
+
+#### Evaluation Datasets
+We evaluated the model on two sets of official JEE Mains 2025 mathematics papers:
+* January Session: 10 question papers containing 250 questions.
+* April Session: 9 question papers containing 225 questions.
+
+Each paper includes a mix of:
+* Multiple Choice Questions (MCQs) with one correct option
+* Numeric Answer Type (NAT) questions requiring precise numerical responses
+
+#### Evaluation Metric
+We used a composite evaluation metric to reflect real-world grading rigor and reduce false positives:
+
+1. Float Match
+  * Compares predicted and target answers within a tolerance (±1e-9)
+  * Handles rounding artifacts and small numerical errors robustly
+2. String Match
+  * Used for symbolic answers (e.g., fractions, radicals)
+  * Uses strict exact match — predictions must match ground truth character-for-character
+3. LLM-as-Judge (GPT-4o-mini)
+  * Used for Mathematical equivalence for ambiguous formats
+
+### 🔹 Accuracy Comparison Across Models
+![](accuracy.png)
+> *Aryabhatta has the best accuracy on JEE Main Maths, on par with frontier models*
+
+### 🔹 Accuracy vs Token Usage
+![](accuracy-vs-token.png)
+> *Aryabhatta is on par with frontier models in terms of accuracy vs token usage*
+
+---
+
+## 🔧 Intended Use
+
+**Primary Use Cases**:
+- Competitive exam preparation (JEE Main level mathematics problems)
+- Question answering and doubt-solving systems
+- Educational tutoring and concept explanation
+
+
+## 💡 How to Use
+
+### 🧪 Using with 🤗 Transformers
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
+
+model_id = "PhysicsWallahAI/Aryabhatta-1.0"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+
+# Define stop strings
+stop_strings = ["<|im_end|>", "<|end|>", "<im_start|>", "⁠```python\n", "⁠<|im_start|>", "]}}]}}]"]
+
+def strip_bad_tokens(s, stop_strings):
+    for suffix in stop_strings:
+        if s.endswith(suffix):
+            return s[:-len(suffix)]
+    return s
+
+
+# Create generation config (can also set temperature, top_p, etc.)
+generation_config = GenerationConfig(
+    max_new_tokens=4096,
+    stop_strings = stop_strings
+)
+
+query = 'Find all the values of \\sqrt[3]{1}'
+messages = [{'role': 'system', 'content': 'Think step-by-step; put only the final answer inside \\boxed{}.'},
+            {'role': 'user', 'content': query}]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+inputs = tokenizer([text], return_tensors="pt")
+outputs = model.generate(**inputs, generation_config=generation_config, tokenizer=tokenizer)
+
+print(strip_bad_tokens(tokenizer.decode(outputs[0], skip_special_tokens=True), stop_strings))
+````
+
+---
+
+### ⚡ Using with vLLM
+
+To run the model efficiently using vLLM:
+
+```python
+from vllm import LLM, SamplingParams
+
+# Initialize model (downloads from Hugging Face if not local)
+llm = LLM(model="PhysicsWallahAI/Aryabhatta-1.0")
+
+# Define prompt and sampling configuration
+query = 'Find all the values of \\sqrt[3]{1}'
+messages = [{'role': 'system', 'content': 'Think step-by-step; put only the final answer inside \\boxed{}.'},
+            {'role': 'user', 'content': query}]
+sampling_params = SamplingParams(temperature=0.0, max_tokens=4*1024, stop=["<|im_end|>", "<|end|>", "<im_start|>", "⁠```python\n", "⁠<|im_start|>", "]}}]}}]"])
+
+# Run inference
+results = llm.chat(messages, sampling_params)
+
+# Print result
+print(results[0].outputs[0].text.strip())
+```
+
+---
+
+## 🚀 Roadmap
+
+**Aryabhatta 2.0** (Upcoming):
+- Extending domain coverage to **Physics** and **Chemistry**
+- Supporting **JEE Advanced**, **NEET**, and **Foundation syllabus**
+- Further optimization for affordability and accuracy in real-time deployments
+
+---
+
+## 🤝 Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{aryabhatta2025,
+  title = {Aryabhatta 1.0: A compact, exam-focused language model tailored for mathematics in Indian competitive exams, especially JEE Main.},
+  author = {Physics Wallah AI Research},
+  year = {2025},
+  note = {\url{https://huggingface.co/PhysicsWallahAI/Aryabhatta-1.0}},
+}