zenlm/zen-legal

Zen Legal

Parameters: 14B | Architecture: Zen 4 Architecture | Context: 131K | License: Apache 2.0 | Released: 2024-10-01

Legal AI for contract analysis, case research, regulatory compliance, and legal document synthesis.

Designed for legal technology developers and researchers. Not legal advice.

Base weights: zenlm/zen4-pro

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("zenlm/zen4-pro", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen4-pro")
messages = [{"role": "user", "content": "Your domain-specific prompt here"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(output[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))

---

The Zen LM Family

Joint research between Hanzo AI (Techstars '17), Zoo Labs Foundation (501c3), and Lux Partners Limited.

All weights Apache 2.0. Download, run locally, fine-tune, deploy commercially.

HuggingFace · Chat · API · Docs