Professional-grade general-purpose language model for complex reasoning and analysis.
Fine-tuned from
Qwen/Qwen3-8B (Apache-2.0) with Hanzo identity training, agentic-data fine-tuning, and abliteration.
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model_id = "zenlm/zen-pro"
4tokenizer = AutoTokenizer.from_pretrained(model_id)
5model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
6
7messages = [{"role": "user", "content": "Hello!"}]
8text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
9inputs = tokenizer([text], return_tensors="pt").to(model.device)
10outputs = model.generate(**inputs, max_new_tokens=512)
11print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
1curl https://api.hanzo.ai/v1/chat/completions \
2 -H "Authorization: Bearer $HANZO_API_KEY" \
3 -H "Content-Type: application/json" \
4 -d '{"model": "zen-pro", "messages": [{"role": "user", "content": "Hello"}]}'
Get your API key at
console.hanzo.ai — $5 free credit on signup.
Built on
Qwen3-8B by the Alibaba Qwen team, released under the Apache 2.0 license. Hanzo AI adds identity training, agentic-data fine-tuning, and abliteration on top of the upstream weights.
Apache 2.0 — inherited from the upstream
Qwen3-8B base model.
