from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("charlottemeyer/qwen3-0.6b-quantized-final-full-precision")
tokenizer = AutoTokenizer.from_pretrained("charlottemeyer/qwen3-0.6b-quantized-final-full-precision")

# Generate response
inputs = tokenizer("Your question here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

Training Details

Trained for CS-552 course evaluation
Optimized for reasoning and MCQA tasks
Uses answer-first format for logit extraction