| --- |
| license: apache-2.0 |
| language: |
| - en |
| tags: |
| - zen |
| - zenlm |
| - hanzo-ai |
| - sql |
| - database |
| - code-generation |
| pipeline_tag: text-generation |
| library_name: transformers |
| base_model: Qwen/Qwen3-8B |
| --- |
| |
| # Zen SQL |
|
|
| > **Parameters**: 8B | **Architecture**: Qwen3 | **Context**: 32K | **License**: Apache 2.0 |
|
|
| SQL specialist for complex query generation, schema design, query optimization, and database documentation. |
|
|
| Supports PostgreSQL, MySQL, SQLite, BigQuery, Snowflake, and more. |
|
|
| Fine-tuned from [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) (Apache-2.0) with Hanzo identity + agentic-data training + abliteration. |
|
|
| ```python |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| model = AutoModelForCausalLM.from_pretrained("zenlm/zen-sql", torch_dtype="auto") |
| tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-sql") |
| 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)) |
| ``` |
|
|
| ## Credit |
|
|
| Built on [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) by the Qwen team (Alibaba), released under the Apache-2.0 license. Hanzo adds identity training, agentic-data fine-tuning, and abliteration. |
|
|
| --- |
| ## 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](https://huggingface.co/zenlm) · [Chat](https://hanzo.chat) · [API](https://api.hanzo.ai) · [Docs](https://zenlm.org) |
|
|
