Update README.md

README.md

@@ -14,7 +14,7 @@ tags:
 - physicswallah
 language:
 - en
-model_name: PhysicsWallah/Aryabhatta-1.0
+model_name: PhysicsWallah/Aryabhata-1.0
 model_creator: Physics Wallah AI Research
 model_type: Causal decoder-based model
 base_model: Qwen/Qwen2.5-Math-7B
@@ -23,10 +23,10 @@ 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.
+**Aryabhata 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, Aryabhata 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.*
+> 🚧 *Aryabhata 1.0 is an **experimental release**. We are actively seeking feedback — please contribute in the Discussion tab of this repo.*
 ---
 
 ## 🧠 Key Features
@@ -51,7 +51,7 @@ pipeline_tag: text-generation
   - **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:
+We began with model merging (Weighted average) to build a strong initialization (Aryabhata 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.
@@ -63,7 +63,7 @@ We extracted ~250K raw questions from Physics Wallah's internal database and app
 Final curated dataset: ~130K high-quality questions.
 
 For each question:
-* Generated 4 CoTs using Aryabhatta 0.5.
+* Generated 4 CoTs using Aryabhata 0.5.
 * Retained only those leading to correct final answers.
 
 Resulting Dataset:
@@ -79,7 +79,7 @@ We used a custom in-house variant of Group Relative Policy Optimization (GRPO),
 
 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.
+This multi-phase training strategy allows Aryabhata 1.0 to capture **pedagogy-aligned reasoning patterns**, making it highly effective for solving real student queries in mathematics.
 
 ---
 
@@ -111,11 +111,11 @@ We used a composite evaluation metric to reflect real-world grading rigor and re
 
 ### 🔹 Accuracy Comparison Across Models
 ![](accuracy.png)
-> *Aryabhatta has the best accuracy on JEE Main Maths, on par with frontier models*
+> *Aryabhata 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*
+> *Aryabhata is on par with frontier models in terms of accuracy vs token usage*
 
 ---
 
@@ -134,7 +134,7 @@ We used a composite evaluation metric to reflect real-world grading rigor and re
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
 
-model_id = "PhysicsWallahAI/Aryabhatta-1.0"
+model_id = "PhysicsWallahAI/Aryabhata-1.0"
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(model_id)
@@ -181,7 +181,7 @@ To run the model efficiently using vLLM:
 from vllm import LLM, SamplingParams
 
 # Initialize model (downloads from Hugging Face if not local)
-llm = LLM(model="PhysicsWallahAI/Aryabhatta-1.0")
+llm = LLM(model="PhysicsWallahAI/Aryabhata-1.0")
 
 # Define prompt and sampling configuration
 query = 'Find all the values of \\sqrt[3]{1}'
@@ -200,7 +200,7 @@ print(results[0].outputs[0].text.strip())
 
 ## 🚀 Roadmap
 
-**Aryabhatta 2.0** (Upcoming):
+**Aryabhata 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
@@ -212,9 +212,9 @@ print(results[0].outputs[0].text.strip())
 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.},
+@misc{Aryabhata2025,
+  title = {Aryabhata 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}},
+  note = {\url{https://huggingface.co/PhysicsWallahAI/Aryabhata-1.0}},
 }