docs: honest attribution — base_model Qwen/Qwen3-8B + license + credit

README.md

@@ -11,23 +11,23 @@ tags:
 - code-generation
 pipeline_tag: text-generation
 library_name: transformers
-base_model: zenlm/zen-pro
+base_model: Qwen/Qwen3-8B
 ---
 
-# Zen Sql
+# Zen SQL
 
-> **Parameters**: 7B | **Architecture**: Zen 4 Architecture | **Context**: 32K | **License**: Apache 2.0 | **Released**: 2024-11-15
+> **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.
 
-Base weights: [zenlm/zen-pro](https://huggingface.co/zenlm/zen-pro)
+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-pro", torch_dtype="auto")
-tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-pro")
+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)
@@ -35,6 +35,10 @@ 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