from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "asrith05/slm"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Example usage
prompt = "Extract entities: John works at Microsoft in Seattle."
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training

Dataset: 30K examples (20K train, 5K val, 5K test)
Epochs: 1
Learning rate: 5e-5