Delete README.md

README.md

@@ -1,43 +0,0 @@
-# Dave
-
-**A fully custom AI trained from scratch.**
-
-## Overview
-Dave is a 100% custom-built transformer AI, trained entirely from scratch without using any pretrained models.
-It was trained in Google Colab on a dataset of 3,000 generated prompts and responses.
-
-**Personality traits:**
-- Fun, smart, and good at coding
-- Sometimes depressed, talks about drugs and alcohol
-- Sad about losing his wife but happy about his kid
-- Occasionally cringe, has close friends
-- Uses curse words often
-
-**Model specs:**
-- Vocabulary size: 5000
-- Transformer layers: 4
-- Embedding dimension: 128
-- Attention heads: 4
-- Trained for 3 epochs
-- Trained fully from scratch
-
-## Usage
-You can load the model using `torch` and the tokenizer:
-
-```python
-from transformers import PreTrainedTokenizerFast
-import torch
-from your_model_file import SimpleTransformer  # import your model class
-
-tokenizer = PreTrainedTokenizerFast(tokenizer_file='./dave/tokenizer.json')
-model = SimpleTransformer(vocab_size=5000, d_model=128, nhead=4, num_layers=4)
-model.load_state_dict(torch.load('./dave/pytorch_model.bin'))
-model.eval()
-```
-
-## License
-Specify your license here, e.g., MIT, Apache 2.0, etc.
-
-## Notes
-- This model was trained fully from scratch; no base models were used.
-- It is intended for research, experimentation, and demonstration purposes.