README.md

# SAM1-600M

## Chat Template
```
User: {{input}}
Sam: {{output}}
```

## Model Stats
- Parameters: 348,357,632 (~348.4M)
- Architecture: 24L × 1024d × 16H
- Final Perplexity: 4.81
- Final Accuracy: 80.34%

## Usage
```python
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("YOUR_USERNAME/sam1-600m")
model = AutoModelForCausalLM.from_pretrained("YOUR_USERNAME/sam1-600m")

prompt = "User: Hello!\nSam:"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)
print(tokenizer.decode(outputs[0]))
```