Upload README.md with huggingface_hub

README.md

@@ -16,8 +16,8 @@ A 90M parameter GPT trained from scratch in Rust using the [picochat](https://gi
 ## Model details
 
 - **Architecture**: Decoder-only transformer with grouped-query attention, RoPE, sliding window attention, ReLU-squared MLP
-- **Parameters**: 90M (depth=8: 8 layers, 512 dim, 8 heads, 4 KV heads)
-- **Vocab size**: 32,768 (BPE tokenizer)
+- **Parameters**: 31.5M (depth=8: 8 layers, 512 dim, 8 heads, 4 KV heads)
+- **Vocab size**: 4,096 (BPE tokenizer)
 - **Context length**: 2048 tokens
 - **Training**: Pretrained on OpenWebText (10k steps), then supervised fine-tuned on UltraChat + no_robots (2k steps)
 - **Framework**: [candle](https://github.com/huggingface/candle) (Rust)
@@ -51,6 +51,6 @@ This model was trained on CPU with limited data (~5M tokens vs GPT-2's 8B). It p
 
 ## Files
 
-- `model.safetensors` -- model weights (345MB)
+- `model.safetensors` -- model weights (120MB)
 - `config.json` -- model architecture config
 - `tokenizer.json` -- BPE tokenizer (32K vocab)