Update README.md

README.md

@@ -1,5 +1,6 @@
 ---
 base_model: unsloth/gpt-oss-120b-unsloth-bnb-4bit
+repo_name: Azmainadeeb/MathGPT
 tags:
 - text-generation-inference
 - transformers
@@ -17,62 +18,62 @@ datasets:
 - brando/olympiad-bench-imo-math-boxed-825-v2-21-08-2024
 - Goedel-LM/MathOlympiadBench
 - hf-imo-colab/olympiads-ref-base-math-word
+- alejopaullier/aimo-external-dataset
+- imbishal7/math-olympiad-problems-and-solutions-aops
+- baidalinadilzhan/problems-and-solutions-interantional-phos
+- kishanvavdara/aimo-olympiadbench-math-dataset
 ---
 
-# GPT-OSS-120B Olympiad Reasoning
+# MathGPT (GPT-OSS-120B-Olympiad)
 
-This model is a specialized fine-tune of **OpenAI's GPT-OSS 120B** (4-bit quantized by Unsloth). It is designed for high-level mathematical reasoning, complex problem solving, and long-form "Thinking" processes.
+**MathGPT** is a high-performance reasoning model fine-tuned from **GPT-OSS 120B**. It is engineered specifically for solving complex mathematical theorems, competition-level problems (AIME/IMO), and advanced scientific reasoning.
 
 - **Developed by:** Azmainadeeb
+- **Model Type:** Causal Language Model (Fine-tuned for Mathematical Reasoning)
 - **Base Model:** unsloth/gpt-oss-120b-unsloth-bnb-4bit
-- **Architecture:** Mixture-of-Experts (MoE) with 117B total and 5.1B active parameters.
-- **License:** Apache-2.0
+- **Training Framework:** Unsloth + TRL
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
 
-## 🌟 Model Highlights
-This model uses the **Harmony Response Format** natively, allowing for a distinct separation between "internal reasoning" and "final response." By fine-tuning on a mixture of thinking traces and competition-grade math, the model exhibits improved logical consistency and accuracy in STEM domains.
+## 🧩 Model Architecture
+MathGPT leverages the **Mixture-of-Experts (MoE)** architecture of the GPT-OSS family, utilizing 117B total parameters with 5.1B active parameters per token. This allows the model to maintain state-of-the-art reasoning depth while remaining computationally efficient during inference.
 
-### Capabilities:
-* **Deep Reasoning:** Leverages the `Multilingual-Thinking` dataset to maintain a coherent chain-of-thought.
-* **Competition Math:** Optimized for International Mathematical Olympiad (IMO) and AIME-style problems.
-* **Variable Effort:** Supports the `reasoning_effort` parameter (low, medium, high) to balance speed and accuracy.
 
 
+## 📚 Training Data
+The model was trained on a massive synthesis of reasoning-dense datasets to ensure "Chain of Thought" consistency:
 
-## 📊 Training Data
-The model was trained on a high-diversity mixture of reasoning and mathematical datasets:
+### Primary Thinking Dataset
+* **[Multilingual-Thinking](https://huggingface.co/datasets/HuggingFaceH4/Multilingual-Thinking):** Instills the core "Thinking" trace and multi-step internal monologue.
 
-1. **[HuggingFaceH4/Multilingual-Thinking](https://huggingface.co/datasets/HuggingFaceH4/Multilingual-Thinking):** Provides the foundational "thinking" behavior and internal monologue.
-2. **[brando/olympiad-bench-imo-math](https://huggingface.co/datasets/brando/olympiad-bench-imo-math-boxed-825-v2-21-08-2024):** High-difficulty math competition problems.
-3. **[Goedel-LM/MathOlympiadBench](https://huggingface.co/datasets/Goedel-LM/MathOlympiadBench):** Challenging math benchmark problems.
-4. **[hf-imo-colab/olympiads-ref-base-math-word](https://huggingface.co/datasets/hf-imo-colab/olympiads-ref-base-math-word):** Diverse word problems and solutions.
-5. **Kaggle External Math Data:** Curated datasets from AoPS, AIMO, and OlympiadBench for extra-domain coverage.
+### Olympiad & Competition Sets
+* **OlympiadBench & MathOlympiadBench:** High-difficulty benchmark problems.
+* **IMO Math Boxed:** Problems curated from the International Mathematical Olympiad.
+* **AoPS (Art of Problem Solving):** Diverse competition-style math problems.
+* **AIMO External Data:** Specific sets designed for the AI Mathematical Olympiad.
 
-## 🛠 Usage Instructions
-This model is optimized for use with the **Unsloth** library and Hugging Face's `transformers`. 
+## 🚀 Quickstart Usage
 
-### Quick Inference Example
 ```python
 from unsloth import FastLanguageModel
-import torch
 
 model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name = "Azmainadeeb/gpt-oss-120b-olympiad", # Replace with your repo ID
-    max_seq_length = 2048,
+    model_name = "Azmainadeeb/MathGPT",
+    max_seq_length = 4096,
     load_in_4bit = True,
 )
 
 messages = [
-    {"role": "user", "content": "Let n be a positive integer such that n^2 + 3n + 2 is a perfect square. Find all such n."}
+    {"role": "user", "content": "Find all real numbers x such that 8^x + 2^x = 130."}
 ]
 
-input_ids = tokenizer.apply_chat_template(
+# Apply the template with reasoning_effort to trigger the "Thinking" mode
+inputs = tokenizer.apply_chat_template(
     messages,
     add_generation_prompt = True,
     reasoning_effort = "medium", # Options: low, medium, high
     return_tensors = "pt"
 ).to("cuda")
 
-outputs = model.generate(input_ids, max_new_tokens = 1024)
+outputs = model.generate(inputs, max_new_tokens = 1024)
 print(tokenizer.decode(outputs[0]))