Update README.md

README.md

@@ -17,7 +17,7 @@ language:
 library_name: transformers
 pipeline_tag: text-generation
 ---
-# Alpie-Core: 4-bit Quantized Reasoning Model
+# Alpie Core: 4-bit Quantized Reasoning Model
 
 📄 **[Technical Report: Alpie Core.pdf](./Alpie_Core.pdf)**
 
@@ -32,7 +32,7 @@ pipeline_tag: text-generation
 
 **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.
+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)
 
@@ -50,7 +50,7 @@ With a dramatically reduced memory footprint, Alpie-Core delivers competitive, f
 
 ## 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, optimised with high-quality LLM-generated responses. The fine-tuning process emphasised 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.
 
@@ -64,7 +64,7 @@ With a dramatically reduced memory footprint, Alpie-Core delivers competitive, f
 
 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 approach allows Alpie-Core to generalize across global and Indian contexts while staying aligned to safe and responsible use guidelines.
+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
 
@@ -98,7 +98,7 @@ This SFT approach enables Alpie-Core to deliver reliable, aligned, and context-a
 ![BBH Benchmark](BBH.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 |
+| 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 |
 |-----------|----------------------|-------------------|-------------|---------------|---------------|----------------|----------------------------|
 | MMLU (5-shot) | **81.28%** | 78.4% | 85.0% | 84.4% | 79.3% | 78.6% | 80.73% |
 | GSM8K (8-shot) | **92.75%** | 81.6% | 88.3% | 83.5% | - | 82.2% | 80.73% |
@@ -107,7 +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.
+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
 
@@ -141,7 +141,7 @@ These results demonstrate Alpie-Core’s ability to rival or surpass leading pro
 
 ### Additional Benchmarks
 
-| Benchmark | Alpie-Core (32B-4bit) | Category |
+| Benchmark | Alpie Core (32B-4bit) | Category |
 |-----------|----------------------|----------|
 | AIME | **47.34%** | Advanced Mathematics |
 | GPQA (Diamond) | **40.91%** | Graduate-level QA |
@@ -173,7 +173,7 @@ These results demonstrate Alpie-Core’s ability to rival or surpass leading pro
 
 ![Carbon Footprint](carbon_footprint.png)
 
-**Carbon Footprint**: We estimated the environmental impact of training Alpie-Core (32B) on 8× NVIDIA H100-80GB GPUs by calculating carbon emissions from GPU energy consumption. The calculation follows the formula:
+**Carbon Footprint**: We estimated the environmental impact of training Alpie Core (32B) on 8× NVIDIA H100-80GB GPUs by calculating carbon emissions from GPU energy consumption. The calculation follows the formula:
 CO₂e (kg) = Grid CO₂ Factor (kg/kWh) × Runtime (hours) × Power per GPU (kW) × Number of GPUs
 
 Training Parameters:
@@ -190,7 +190,7 @@ 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.*
+*This makes Alpie Core one of the most carbon-efficient reasoning models released to date.*
 
 ## 9. Use Cases
 
@@ -210,7 +210,7 @@ Best for **STEM**, **complex mathematical reasoning**, **coding**, and **Indian
 ## 10. Safety and Limitations
 
 ### Enhanced Content Access
-Unlike the base DeepSeek model, Alpie-Core provides factual, balanced responses to geopolitically sensitive questions, offering global accessibility and factual accuracy on topics like Taiwan's status, Arunachal Pradesh sovereignty, and other sensitive geopolitical issues.
+Unlike the base DeepSeek model, Alpie Core provides factual, balanced responses to geopolitically sensitive questions, offering global accessibility and factual accuracy on topics like Taiwan's status, Arunachal Pradesh sovereignty, and other sensitive geopolitical issues.
 
 ### Current Limitations
 - Multilingual reasoning in Hindi/Hinglish shows room for improvement
@@ -317,8 +317,8 @@ with torch.no_grad():
 ## 12. Citation
 
 ```bibtex
-@misc{alpie2025core,
-  title     = {Alpie-Core: A 4-bit Quantized Reasoning Model Surpassing Full-Precision Benchmarks},
+@misc{169pi2025alpiecore,
+  title     = {Alpie-Core: A 4-Bit Quantized Reasoning Model from India that Outperforms Full-Precision Models},
   author    = {169Pi AI},
   year      = {2025},
   url       = {https://huggingface.co/alpie/Alpie-Core}
@@ -354,5 +354,5 @@ We are also grateful to the Hugging Face ecosystem (Transformers, PEFT, vLLM, bi
 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.  
+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.*