Update README.md

README.md

@@ -1,23 +1,38 @@
-# Dave – Fully Custom AI Model
+# ──────────────────────────────
+# Prepare "Dave" Hugging Face-ready repo
+# ──────────────────────────────
 
-**Model type:** Fully Custom Transformer from Scratch  
-**Purpose:** Conversational AI with a unique personality: fun, smart, coding-savvy, sometimes sad or depressed, talks about drugs and alcohol, lost his wife, happy about his kid, sometimes cringe, close friends, swears often.
+!pip install -q torch transformers tokenizers
 
-**Training:**  
-- 3000 generated prompts and responses  
-- Custom tokenizer and transformer trained from scratch  
-- Trained entirely in Google Colab  
-- Saved as `pytorch_model.bin`, `config.json`, `tokenizer.json`
+import os
+import json
+import torch
+import torch.nn as nn
+from tokenizers import Tokenizer, models, pre_tokenizers, trainers, processors
 
-**Example usage:**
+# -----------------------------
+# Settings
+# -----------------------------
+model_name = "dave"
+output_dir = f"./{model_name}"
+os.makedirs(output_dir, exist_ok=True)
+print(f"Using folder: {output_dir}")
+
+# -----------------------------
+# README.md for Hugging Face
+# -----------------------------
+readme_content = """# Dave – Fully Custom AI Model
+
+Dave is a fully custom-built transformer trained from scratch.
+- Personality: fun, smart, coding-savvy, depressed, talks about drugs/alcohol, lost wife, has a kid, sometimes cringe, has close friends, swears frequently.
+- 3000 prompts/responses were used for training.
+- Architecture: custom Transformer implementation.
+- Trained from scratch.
+
+## How to use
 
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 tokenizer = AutoTokenizer.from_pretrained("DSDUDEd/Dave")
 model = AutoModelForCausalLM.from_pretrained("DSDUDEd/Dave")
-
-prompt = "Write a Python function to reverse a string."
-inputs = tokenizer(prompt, return_tensors="pt")
-outputs = model.generate(**inputs, max_new_tokens=64)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))