Upload README.md with huggingface_hub

README.md

@@ -11,6 +11,7 @@ tags:
 - swiglu
 - rope
 - pytorch
+- gradio
 library_name: custom
 ---
 
@@ -18,6 +19,12 @@ library_name: custom
 
 A **89.8M parameter** causal language model built entirely from scratch using a custom transformer architecture, trained on WikiText-103 + synthetic instruction data.
 
+## Try it Online
+
+You can try Nexus SmAll v1 directly in your browser using the Hugging Face Space below:
+
+👉 **[Nexus SmAll v1 Chat](https://huggingface.co/spaces/JustScriptzz/nexus-smAll-v1)**
+
 ## Architecture
 
 | Parameter | Value |
@@ -42,15 +49,29 @@ Key design choices:
 
 ## Installation
 
+Requirements: Python 3.8+ and pip.
+
 ```bash
-git clone https://huggingface.co/MarcoTesting/nexus-smAll-v1
+# 1. Clone the repository
+git clone https://huggingface.co/JustScriptzz/nexus-smAll-v1
 cd nexus-smAll-v1
-pip install torch tokenizers
+
+# 2. Install dependencies
+pip install torch --index-url https://download.pytorch.org/whl/cpu
+pip install tokenizers
 ```
 
+> **GPU users**: Replace `--index-url https://download.pytorch.org/whl/cpu` with the appropriate CUDA version, e.g. `--index-url https://download.pytorch.org/whl/cu124` for CUDA 12.4.
+
 ## Usage
 
-### Chat
+### Command line (quick start)
+
+```bash
+python chat.py --weights weights/nexus_instruct.pt
+```
+
+### Python API
 
 ```python
 from src.model import Nexus
@@ -67,22 +88,15 @@ model.eval()
 
 tokenizer = Tokenizer.from_file("data/tokenizer.json")
 
-prompt = "<|user|>\nWhat is Python?\n<|assistant|>\n"
+prompt = "User: What is Python?\nAssistant:"
 encoded = tokenizer.encode(prompt)
 tokens = torch.tensor([encoded.ids])
 
 output, _ = model.generate(tokens, max_new_tokens=64, temperature=0.2, top_k=40, top_p=0.9)
 reply = tokenizer.decode(output)
-
 print(reply)
 ```
 
-### Command line
-
-```bash
-python chat.py --weights weights/nexus_instruct.pt
-```
-
 ## Training
 
 - **Phase 1**: 100k steps on WikiText-103 (next-token prediction, ~212k sequences)