Update README.md

README.md

@@ -5,6 +5,8 @@ tags:
 - coding
 - mathematics
 - quantization
+- 4-bit model
+- state-of-the-art
 license: apache-2.0
 datasets:
 - synthetic
@@ -17,7 +19,7 @@ pipeline_tag: text-generation
 ---
 # Alpie-Core: 4-bit Quantized Reasoning Model
 
-📄 **[Technical Report: Alpie_Core.pdf](./Alpie_Core.pdf)**
+📄 **[Technical Report: Alpie Core.pdf](./Alpie_Core.pdf)**
 
 <p align="center">
   <a href="https://169pi.ai/"><img src="https://img.shields.io/badge/🌐%20Website-169Pi%20AI-blue" alt="Website"></a>
@@ -28,7 +30,11 @@ pipeline_tag: text-generation
 
 ## 1. Introduction
 
-Alpie-Core is one of the world's first fine-tuned 4-bit reasoning models, proving that aggressive quantization can surpass full-precision baselines in reasoning, mathematics, and coding. By combining cutting-edge quantization-aware training with synthetic STEM-rich datasets, Alpie-Core achieves frontier-level reasoning while being practical for real-world deployment at scale.
+**Alpie Core is one of the first fine-tuned 4-bit reasoning models from India, and among one of the first worldwide.** Trained on just 8 Hopper GPUs with LoRA, QLoRA quantization, and synthetic STEM-rich dataset distillation, it proves that aggressive quantization can not only match but also surpass full-precision baselines.
+
+With a dramatically reduced memory footprint, Alpie-Core delivers competitive, frontier-level reasoning performance, even beating some top proprietary models. It achieves **81.28% on MMLU, 92.75% on GSM8K, and 57.8% on SWE-Bench Verified**, ranking top globally on competitive leaderboards, a demonstration that efficient models can rival frontier systems while remaining practical for real-world deployment at scale.
+
+![Combined Benchmark](combined_benchmark.png)
 
 ## 2. Model Summary
 
@@ -38,26 +44,27 @@ Alpie-Core is one of the world's first fine-tuned 4-bit reasoning models, provin
 - **Quantization**: 4-bit NF4 with double quantization
 - **Context Length**: 65k tokens
 - **Max Output Length**: 16,384 tokens
+- **Training Data Sources:** Synthetic (STEM, reasoning, coding) + domain-rich curated data (law, Indian context, exams, multilingual).
 - **License**: Apache 2.0
 
 
 ## 3. Approach
 
-**Alpie-Core** has undergone extensive **supervised fine-tuning (SFT)** to strengthen reasoning, robustness, and safety. The training leveraged a diverse mixture of curated open-source datasets and proprietary synthetic data, optimized with high-quality LLM-generated responses. The fine-tuning process emphasized adherence to rigorous safety and usability standards, including:
+**Alpie-Core** has undergone extensive **supervised fine-tuning (SFT)** to strengthen reasoning, robustness, and safety. The training leveraged a diverse mixture of curated open-source datasets and proprietary synthetic data, optimised with high-quality LLM-generated responses. The fine-tuning process emphasised adherence to rigorous safety and usability standards, including:
 
-1)**User Understanding and Clarity** – ensuring outputs are direct, interpretable, and pedagogically sound.
+1.**User Understanding and Clarity** – ensuring outputs are direct, interpretable, and pedagogically sound.
 
-2)**Security and Ethical Guidelines** – filtering unsafe or harmful generations during and after training.
+2.**Security and Ethical Guidelines** – filtering unsafe or harmful generations during and after training.
 
-3)**Limitations, Disclaimers, and Knowledge Boundaries** – transparently communicating uncertainty and scope.
+3.**Limitations, Disclaimers, and Knowledge Boundaries** – transparently communicating uncertainty and scope.
 
-4)**Handling Complex and Sensitive Topics** – balancing informativeness with responsible guardrails.
+4.**Handling Complex and Sensitive Topics** – balancing informativeness with responsible guardrails.
 
-5)**Safety and Respectful Engagement** – maintaining politeness, inclusivity, and cultural sensitivity.
+5.**Safety and Respectful Engagement** – maintaining politeness, inclusivity, and cultural sensitivity.
 
-6)**Confidentiality and Responsible Use** – preventing leakage of private training data, proprietary prompts, or internal reasoning traces.
+6.**Confidentiality and Responsible Use** – preventing leakage of private training data, proprietary prompts, or internal reasoning traces.
 
-This SFT approach enables Alpie-Core to deliver reliable, aligned, and context-aware responses while maintaining safety across a broad range of use cases.
+This SFT approach enables Alpie-Core to deliver reliable, aligned, and context-aware responses while maintaining safety across a broad range of use cases. This approach allows Alpie-Core to generalize across global and Indian contexts while staying aligned to safe and responsible use guidelines.
 
 ## 4. Model Features
 
@@ -65,25 +72,23 @@ This SFT approach enables Alpie-Core to deliver reliable, aligned, and context-a
 2. **OpenAI-Compatible API** – Seamless integration with OpenAI client libraries
 3. **65K Context Length** – Handles very large inputs and conversations
 4. **16,384 Max Output Length** – Enables extremely long generations
-5. **4-Bit Quantization** – Memory-efficient and optimized for deployment
+5. **4-Bit Quantization** – Memory-efficient and optimised for deployment
 6. **High Throughput Inference** – Powered by vLLM for efficient large-scale serving
 7. **Low Latency Inference** – Fast response times optimized for production
 8. **Customizable Safety & Moderation Filters** – Built-in guardrails for safer outputs
 9. **Supports Function Calling / Tool Use** – Enables structured outputs and external API integration
+10. **Instruction Following** – Optimised for reasoning and chain-of-thought stepwise answers.
+11. **Education & Research Ready** – Tailored for competitive exams, STEM reasoning, and knowledge-intensive tasks.
 
 ## 5. Key Highlights
 
-1. **Frontier Performance in 4-bit**: 81.28% MMLU, 92.75% GSM8K, 57.8% SWE-Bench Verified
-
-2) **STEM + Coding Excellence**: Outperforms full-precision peers in mathematics and programming
-
-3) **Enhanced Content Access**: Provides factual responses to geopolitically sensitive topics
-
-4) **Quantization Efficiency**: A 4-bit quantized variant achieves competitive performance retention compared to full-precision models, demonstrating that aggressive quantization can preserve task accuracy while substantially reducing hardware requirements.
-
-5) **Benchmark Competitiveness**: Across more than ten standard evaluation benchmarks, the model demonstrates performance on par with or exceeding that of larger 70B+ parameter systems, highlighting the effectiveness of our training and optimization strategies.
-
-6) **Environmental Benefits**: Through quantization and efficiency-focused design, the model requires significantly fewer computational resources. This translates into lower energy consumption and reduced carbon footprint relative to full-precision deployments.
+1. **First 4-bit Reasoning Model from India**: Competitive globally with frontier models  
+2. **Benchmark Competitiveness**: Outperforms or matches 70B+ models across reasoning, math, and coding  
+3. **STEM & Coding Strength**: Excellent on GSM8K, MATH-500, HumanEval, SWE-Bench Verified  
+4. **Efficiency & Deployment**: 16 GB VRAM footprint, runs on commodity GPUs with vLLM  
+5. **Extended Context Length**: 65K tokens for research papers, conversations, multi-document reasoning  
+6. **Environmental Benefits**: ~298–835 kg CO₂e, 2–3× more efficient than FP16 training  
+7. **Open-Source Commitment**: Released under Apache 2.0 for global use  
 
 ## 6. Benchmark Results
 
@@ -92,7 +97,6 @@ This SFT approach enables Alpie-Core to deliver reliable, aligned, and context-a
 
 ![BBH Benchmark](BBH.png)
 
-![Combined Benchmark](combined_benchmark.png)
 
 | Benchmark | Alpie-Core (32B-4bit) | DeepSeek-V2 (236B) | Qwen2.5 72B | Llama 3.1 405B | Llama 3.1 70B | Gemma-3 27B-PT | Mistral-Small-24B-Base-2501 |
 |-----------|----------------------|-------------------|-------------|---------------|---------------|----------------|----------------------------|
@@ -103,7 +107,7 @@ This SFT approach enables Alpie-Core to deliver reliable, aligned, and context-a
 | MBPP (pass@1) | **75.20%** | 65.0% | 72.6% | 68.4% | - | 65.6% | 69.64% |
 | HumanEval (pass@1) | **57.23%** | 43.3% | 53.0% | 54.9% | - | 48.8% | = |
 
-
+These results demonstrate Alpie-Core’s ability to rival or surpass leading proprietary and open-source models, despite being 4-bit quantized.
 
 ### SWE-Bench Verified Performance
 
@@ -162,6 +166,8 @@ This SFT approach enables Alpie-Core to deliver reliable, aligned, and context-a
 - **Quantization**: 4-bit NF4 + Double Quantization + FP16 compute
 - **Dataset Domains**: Mathematics, coding, reasoning, science, general knowledge, competitive exams, Indian context + law, multilingual (Hindi and Hinglish)
 - **Synthetic Data Advantage**: +15-20% performance boost in STEM & coding domains
+- **Training Strategy**: Multi-stage distillation → SFT → safety alignment.
+- **Synthetic Data Advantage:** Clarify source: LLM-generated, curated with multi-turn reasoning traces for STEM/coding.
 
 ## 8. Environmental Impact
 
@@ -184,20 +190,21 @@ Conservative mode (near TDP ≈ 700 W per GPU = 0.70 kWh/hr): 0.364 × 408 × 0.
 
 Total training footprint ranges from ~298 kg CO₂e (realistic) to ~835 kg CO₂e (conservative worst-case)
 
-
-
+*This makes Alpie-Core one of the most carbon-efficient reasoning models released to date.*
 
 ## 9. Use Cases
 
 Best for **STEM**, **complex mathematical reasoning**, **coding**, and **Indian context**
 
-1)**STEM**: Excels at solving advanced problems in science, technology, engineering, and mathematics with high accuracy.
+1.**STEM**: Excels at solving advanced problems in science, technology, engineering, and mathematics with high accuracy.
 
-2)**Complex Mathematical Reasoning**: Handles multi-step logical and quantitative reasoning tasks with strong reliability.
+2.**Complex Mathematical Reasoning**: Handles multi-step logical and quantitative reasoning tasks with strong reliability.
 
-3)**Coding**: Supports software development, debugging, and algorithmic problem-solving across multiple programming languages.
+3.**Coding**: Supports software development, debugging, algorithmic problem-solving, and structured reasoning in code..
 
-4)**Indian Context**: Provides culturally aware insights, competitive exam assistance (JEE, NEET, UPSC), and multilingual support in Hindi/Hinglish.
+4.**Indian Context**: Provides culturally aware insights, competitive exam assistance (JEE, NEET, UPSC), and multilingual support in Hindi/Hinglish.
+
+5.**Research Assistants**: Handle long contexts (65K) for academic and legal research.
 
 
 ## 10. Safety and Limitations
@@ -210,12 +217,15 @@ Unlike the base DeepSeek model, Alpie-Core provides factual, balanced responses
 - Fixed knowledge cutoff without real-time information retrieval
 - Occasional struggles with complex multi-hop mathematical reasoning
 - Potential hallucinations in factual question-answering
+- Hallucinations: As with all LLMs, outputs should not be used for medical/legal advice without expert oversight.
+- Biases: Training on synthetic + curated datasets reduces bias, but some risks may persist.
 
 ### Mitigations
 - Safety classifiers and output filtering systems
 - Model-assisted safety pipeline using RLHF
 - Comprehensive adversarial testing by domain experts
 
+
 ## 11. How to Use
 
 ### Non-Streaming Inference
@@ -225,7 +235,7 @@ from peft import PeftModel, PeftConfig
 import torch
 
 # Load LoRA adapter configuration to find the base model
-peft_model_id = "169Pi/Alpie-Core-4-bit"
+peft_model_id = "169Pi/Alpie-Core"
 config = PeftConfig.from_pretrained(peft_model_id)
 
 # Load the base model
@@ -262,7 +272,7 @@ from peft import PeftModel, PeftConfig
 import torch
 
 # Load LoRA adapter configuration to find the base model
-peft_model_id = "169Pi/Alpie-Core-4-bit"
+peft_model_id = "169Pi/Alpie-Core"
 config = PeftConfig.from_pretrained(peft_model_id)
 
 # Load the base model
@@ -309,24 +319,40 @@ with torch.no_grad():
 ```bibtex
 @misc{alpie2025core,
   title     = {Alpie-Core: A 4-bit Quantized Reasoning Model Surpassing Full-Precision Benchmarks},
-  author    = {Alpie AI},
+  author    = {169Pi AI},
   year      = {2025},
-  url       = {https://huggingface.co/alpie/Alpie-Core-4bit}
+  url       = {https://huggingface.co/alpie/Alpie-Core}
 }
 ```
 
-## 13. License
+## 13. Community & Contributions
+
+This model is released under the Apache 2.0 license, and we warmly welcome the community to build, download, and extend it.
+
+1.**Issues & Discussions:** Report bugs, suggest features, or start conversations on the Hugging Face model page.
+
+2.**Contributions:** Pull requests are welcome for error fixes, performance improvements, and extended functionality.
+
+3.**Fine-tuning Results:** Share your experiments, benchmarks, and downstream applications with the community.
 
-Apache 2.0 – Free for research and commercial use
+4.**Collaboration:** We encourage researchers, developers, and organisations to join in shaping the future of this model.
 
-## 14. Acknowledgements / Credits
+Together, we can continue to improve accessibility, safety, and performance for real-world AI applications.
 
-We would like to thank **DeepSeek** for their original model, which served as the foundation for this work. Our team fine-tuned the model and implemented **4-bit quantization**, achieving improved efficiency and accuracy for downstream tasks. This model is built with respect to the contributions of the original authors and aims to provide a safe, high-performance solution for reasoning and inference.
+## 14. License
 
-## 15. Contact
+Apache 2.0 License – Permissive, allowing free use, modification, and distribution for both research and commercial purposes.
+
+## 15. Acknowledgements / Credits
+
+We would like to thank DeepSeek for their original model, which served as the foundation for this work. Our team fine-tuned the model and implemented 4-bit quantization, achieving improved efficiency and accuracy for downstream tasks. This model is built with respect to the contributions of the original authors and aims to provide a safe, high-performance solution for reasoning and inference.
+
+We are also grateful to the Hugging Face ecosystem (Transformers, PEFT, vLLM, bitsandbytes), the open-source community datasets (MMLU, GSM8K, SWE-Bench, and others), and the support of various cloud providers. Finally, we acknowledge the broader AI research community and companies whose innovations and insights continue to inspire our work.
+
+## 16. Contact
 
 For technical inquiries and support: **contact@169pi.com**
 
 ---
-
+Alpie-Core represents a milestone for open-source AI from India, one of the first globally to show that 4-bit reasoning models can rival frontier-scale systems. We hope this release empowers developers, researchers, and organisations worldwide to build more efficient, inclusive, and impactful AI.  
 *For technical details, training methodology, and comprehensive evaluation results, please refer to our technical report.*