updated readme.md
Browse files
README.md
CHANGED
|
@@ -28,41 +28,23 @@ Nandi-150M brings the following key features:
|
|
| 28 |
|
| 29 |
- Strong **multilingual capability** across English and Indic languages
|
| 30 |
- Efficient design enabling **high performance at small scale (150M parameters)**
|
| 31 |
-
- Improved training stability via **layer rescaling and z-loss regularization**
|
| 32 |
- Reduced memory footprint using **factorized embeddings**
|
| 33 |
- Better parameter efficiency through **layer sharing**
|
| 34 |
-
- **Grouped Query Attention (GQA)** for faster inference
|
| 35 |
-
- **RoPE-based positional encoding** for improved sequence modeling
|
| 36 |
|
| 37 |
**This repo contains the base Nandi-150M model**, which has the following features:
|
| 38 |
|
| 39 |
- Type: Causal Language Model
|
| 40 |
- Training Stage: Pretraining (from scratch)
|
| 41 |
- Architecture: Transformer decoder with RoPE, RMSNorm, SwiGLU, GQA, tied embeddings
|
| 42 |
-
- Number of
|
| 43 |
-
- Number of Layers: 16
|
| 44 |
-
- Number of Attention Heads: 16 (Q) / 4 (KV)
|
| 45 |
- Context Length: 2,048 tokens
|
| 46 |
- Vocabulary Size: 131,072
|
| 47 |
-
- Embedding: Factorized (rank = 196)
|
| 48 |
-
- Precision: bfloat16
|
| 49 |
|
| 50 |
## 🌍 Supported Languages
|
| 51 |
|
| 52 |
The model is trained on English and a diverse set of Indic languages, including (but not limited to):
|
| 53 |
|
| 54 |
-
- Hindi
|
| 55 |
-
- Bengali
|
| 56 |
-
- Tamil
|
| 57 |
-
- Telugu
|
| 58 |
-
- Marathi
|
| 59 |
-
- Gujarati
|
| 60 |
-
- Kannada
|
| 61 |
-
- Malayalam
|
| 62 |
-
- Punjabi
|
| 63 |
-
- Odia
|
| 64 |
-
|
| 65 |
-
---
|
| 66 |
|
| 67 |
## 🚀 Usage
|
| 68 |
|
|
@@ -78,4 +60,23 @@ prompt = "Explain transformer in simple words."
|
|
| 78 |
inputs = tokenizer(prompt, return_tensors="pt")
|
| 79 |
|
| 80 |
outputs = model.generate(**inputs, max_new_tokens=100)
|
| 81 |
-
print(tokenizer.decode(outputs[0]))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
- Strong **multilingual capability** across English and Indic languages
|
| 30 |
- Efficient design enabling **high performance at small scale (150M parameters)**
|
|
|
|
| 31 |
- Reduced memory footprint using **factorized embeddings**
|
| 32 |
- Better parameter efficiency through **layer sharing**
|
|
|
|
|
|
|
| 33 |
|
| 34 |
**This repo contains the base Nandi-150M model**, which has the following features:
|
| 35 |
|
| 36 |
- Type: Causal Language Model
|
| 37 |
- Training Stage: Pretraining (from scratch)
|
| 38 |
- Architecture: Transformer decoder with RoPE, RMSNorm, SwiGLU, GQA, tied embeddings
|
| 39 |
+
- Number of Layers: 16*2
|
|
|
|
|
|
|
| 40 |
- Context Length: 2,048 tokens
|
| 41 |
- Vocabulary Size: 131,072
|
|
|
|
|
|
|
| 42 |
|
| 43 |
## 🌍 Supported Languages
|
| 44 |
|
| 45 |
The model is trained on English and a diverse set of Indic languages, including (but not limited to):
|
| 46 |
|
| 47 |
+
- Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Odia
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
|
| 49 |
## 🚀 Usage
|
| 50 |
|
|
|
|
| 60 |
inputs = tokenizer(prompt, return_tensors="pt")
|
| 61 |
|
| 62 |
outputs = model.generate(**inputs, max_new_tokens=100)
|
| 63 |
+
print(tokenizer.decode(outputs[0]))
|
| 64 |
+
```
|
| 65 |
+
|
| 66 |
+
## 📝 Upcoming Releases & Roadmap
|
| 67 |
+
|
| 68 |
+
We’re just getting started with the Nandi series 🚀
|
| 69 |
+
|
| 70 |
+
- **Nandi-150M (Base)** — *Available now*
|
| 71 |
+
- **Nandi-150M (Instruct)** — Coming soon (open-sourced)
|
| 72 |
+
- **Nandi-500M (Base + Instruct)** — Planned next
|
| 73 |
+
- **Nandi-1B (Base + Instruct)** — Final milestone in the current roadmap
|
| 74 |
+
|
| 75 |
+
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.
|
| 76 |
+
|
| 77 |
+
📢 **Blogs & technical deep-dives coming soon**, where we’ll share:
|
| 78 |
+
- Architecture decisions and design trade-offs
|
| 79 |
+
- Training insights and dataset composition
|
| 80 |
+
- Benchmarks and real-world applications
|
| 81 |
+
|
| 82 |
+
Stay tuned!
|