Updated Readme.md

README.md

@@ -0,0 +1,148 @@
+---
+license: apache-2.0
+language:
+- en
+- hi
+- mr
+- ta
+- te
+- kn
+- ml
+- bn
+- pa
+- gu
+- or
+pipeline_tag: text-generation
+library_name: transformers
+base_model:
+- Rta-AILabs/Nandi-Mini-150M
+---
+
+# Nandi-Mini-150M-Instruct
+
+## Introduction
+
+Nandi-Mini-150M-Instruct is a compact, efficient multilingual language model designed for strong performance in resource-constrained environments. It is pre-trained from scratch on 525 billion tokens and further enhanced through instruction tuning and Direct Preference Optimization (DPO). The model supports English and 10 Indic languages.
+
+We do not employ any benchmaxing tricks; the model is designed to be genuinely strong and highly effective for fine-tuning on downstream tasks. 
+
+Nandi-Mini-150M-Instruct focuses on maximizing performance per parameter through architectural efficiency rather than scale. It is optimized for edge devices, on-prem deployments, and low-latency applications, making it ideal for resource-constrained environments.
+Nandi-Mini-150M-Instruct brings the following key features:
+
+- Strong **multilingual capability** across English and Indic languages
+- Efficient design enabling **high performance at small scale (150M parameters)**
+- Reduced memory footprint using **factorized embeddings**
+- Better parameter efficiency through **layer sharing**
+
+## 📝 Upcoming Releases & Roadmap
+
+We’re just getting started with the Nandi series 🚀
+
+- **Nandi-Mini-150M-Tool-Calling** — Coming Soon
+- **Nandi-Mini-500M (Base + Instruct)** — Pre-Training Going On
+- **Nandi-Mini-1B (Base + Instruct)** — Pre-Training Going On
+
+We are actively working on expanding the Nandi family to cover a wider range of use cases—from lightweight edge deployments to more capable instruction-tuned systems.
+
+📢 **Blogs & technical deep-dives coming soon**, where we’ll share:
+- Architecture decisions and design trade-offs  
+- Training insights and dataset composition  
+- Benchmarks and real-world applications  
+
+Stay tuned!
+
+**This repo contains the instruct Nandi-Mini-150M model**, which has the following features:
+
+- Type: Causal Language Model
+- Training Stage: Pretraining (from scratch)
+- Architecture: Transformer decoder with RoPE, RMSNorm, SwiGLU, GQA, tied embeddings, **factorize embeddings**
+- Number of Layers: 16*2 [Layer Sharing, effective layer =32]
+- Context Length: 2,048 tokens
+- Vocabulary Size: 131,072
+
+## 🌍 Supported Languages
+
+The model is trained on English and a diverse set of Indic languages, including:
+
+- Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Odia
+
+## Benchmark Results
+
+## 📊 Benchmark Comparison (~150M Class)
+
+| Model Name         | Parameters | Tokens(B) | HellaSwag | Winogrande | GPQA  | MMLU | GSM8K | HumanEval | Average |
+|------------------|---------------|------------------|----------|------------|------|------|-------|-----------|---------|
+| Mobile-LLM-125M  | 125           | 1000             | 38.90    | 53.10  | -    | -    | -     | -         | -       |
+| SmolLM-135M-Base | 135           | 600              | 42.66| 53.03  | 25.44| 25.30| 1.36  | 0.00      | 24.63   |
+| SmolLM2-135M-Base| 135           | 2000             | 43.13| 53.27  | 22.09| 24.09| 1.74  | 0.00      | 24.05   |
+| **Nandi-Mini-150M-Base-Instruct** | **150**     | **500**          | 37.20    | 52.32      | **28.57** | **28.86** | **2.58** | **4.27** | **25.63** |
+
+
+## 📊 Model Benchmark Comparison With Slightly Bigger Models (350M–600M Class)
+
+| Model Name            | Parameters | Tokens(B) | HellaSwag | Winogrande | GPQA  | MMLU | GSM8K | HumanEval | Average |
+|---------------------|---------------|------------------|----------|------------|------|------|-------|-----------|---------|
+| Mobile-LLM-360M     | 350           | 1000             | 49.60    | 56.59      | -    | -    | -     | -         | -       |
+| Qwen-2-0.5-Base     | 500           | 12000            | 49.01    | 57.69      | 27.23| 44.06| 10.61 | 22.56     | 35.19   |
+| Qwen2.5-0.5B-Base   | 500           | 18000            | 52.16    | 56.82      | 24.10| 47.41| 4.77  | 29.87     | 35.86   |
+| Qwen3-0.6B-Base     | 600           | 36000            | 53.77    | 59.19      | 30.80| 50.34| 15.31 | 28.04     | 39.58   |
+| SmolLM-360M-Base    | 360           | 600              | 53.33    | 57.22      | 21.20| 24.92| 2.19  | 1.21      | 26.68   |
+| SmolLM2-360M-Base   | 360           | 4000            | 56.30    | 59.19      | 25.22| 25.55| 2.88  | 0.00      | 28.19   |
+| **Nandi-Mini-150M-Base** | **150**       | 500          | 37.20| 52.32  | 28.57 | 28.86 | 2.58 | 4.27 | 25.63 |
+
+### Note
+Human-Eval, IfEval & GSM8K have been evaluated using Greedy-decoding for now for all models.
+
+
+
+## 🚀 Usage
+
+```python
+!pip install transformers=='5.4.0'
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+
+model_name = "Rta-AILabs/Nandi-mini-150M-Instruct"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    trust_remote_code=True,
+    device_map="auto",          
+).eval()
+
+prompt = """
+Explain Newton's second Law of Motion
+"""
+model_inputs = tokenizer([prompt], return_tensors="pt").to(model.device)
+
+outputs = model.generate(
+    **model_inputs,
+    max_new_tokens=50,
+    do_sample=True,
+    temperature=0.3,
+    top_k=20,
+    repetition_penalty=1.1,
+    top_p=0.95
+)
+
+response = tokenizer.decode(
+    outputs[0],
+    skip_special_tokens=True,
+)
+
+print(response)
+```
+
+
+
+## 📬 Feedback & Suggestions
+
+We’d love to hear your thoughts, feedback, and ideas!
+
+- **Email:** support@rtaailabs.com
+- **Official Website** https://rtaailabs.com/ 
+- **LinkedIn:** https://www.linkedin.com/company/rta-ai-lab  
+- **X (Twitter):** https://x.com/Rta_AILabs