from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "Maxes-drew/drew-complete-legal-ai",
    torch_dtype=torch.float16,
    device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained("Maxes-drew/drew-complete-legal-ai")

# Legal consultation example
prompt = "Analyze this contract for potential risks:"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=500)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

Training Details:

Base Model: Qwen2.5-Coder-7B-Instruct
Original Training: Drew&#x27;s conversation patterns and expertise
Legal Expertise: Trained on 20,217 legal documents

Legal Documents: 20,217 examples
Loss Improvement: 95% (2.66 → 0.135)
Training Method: LoRA + Full Merge
Specialization: Legal analysis and consulting

This model represents a complete AI legal consultant with specialized expertise.