Update README.md

README.md

@@ -7,6 +7,8 @@ NanoRush Chat is a 283M parameter GPT-style causal language model fine-tuned for
 
 Github- https://github.com/Amogh1221/NanoRush
 
+Live- https://nano-chat-web.vercel.app
+
 ## Model Details & Configuration
 | Detail | Value |
 | --- | --- |
@@ -18,10 +20,8 @@ Github- https://github.com/Amogh1221/NanoRush
 | **Embedding Dimension (n_embd)** | 768 |
 | **Number of Heads (n_head)** | 12 |
 | **Number of Layers (n_layer)** | 36 |
-| **Base Model** | Custom pre-trained NanoRush checkpoint. |
-| **Fine-tuning Dataset** | Fine-tuned on the `HuggingFaceTB/smoltalk` dataset (a curated subset of the UltraChat 200k conversational dataset) using a supervised fine-tuning (SFT) approach. |
-| **Hardware & Optimizations** | The fine-tuning process was fully optimized for A100/H100 GPUs leveraging TF32 precision, BFloat16 autocast, and `torch.compile` for maximum throughput. |
-| **Training Strategy** | Trained using the AdamW optimizer with a cosine learning rate schedule and linear warmup. It utilizes gradient accumulation and auto-scales the batch size based on available VRAM and sequence length. |
+| **Base Model** | Custom pre-trained |
+| **Fine-tuning Dataset** | `HuggingFaceTB/smoltalk`  |
 
 ## Evaluation Results
 
@@ -42,7 +42,8 @@ The model was evaluated using standard zero-shot accuracy metrics.
 
 ## Usage
 
-This model has been exported to be fully compatible with the Hugging Face `transformers` library. You can load it using the standard `AutoModelForCausalLM` pipeline.
+This model has been exported to be fully compatible with the Hugging Face `transformers` library. 
+You can load it using the standard `AutoModelForCausalLM` pipeline.
 
 ### Installation
 Make sure you have the latest version of the `transformers` and `torch` libraries installed:
@@ -50,9 +51,8 @@ Make sure you have the latest version of the `transformers` and `torch` librarie
 pip install torch transformers
 ```
 
-### Example Code (with Streaming & CPU Quantization)
+### Example Code
 
-The following example demonstrates how to run NanoRush Chat efficiently on a CPU using INT8 dynamic quantization and streaming output (as used in the NanoRush web backend).
 
 ```python
 import torch