---

license: apache-2.0

license_link: https://huggingface.co/Qwen/Qwen2.5-0.5B/blob/main/LICENSE language:

- en

pipeline_tag: text-generation

library_name: transformers

---

license: apache-2.0

base_model: Qwen/Qwen2.5-0.5B

tags:

- qwen
- schema-aware
- structured-output
- preweb

---

Qwen2.5-0.5B-Preweb-Base

This model is a derivative base model of Qwen/Qwen2.5-0.5B.

It extends the tokenizer vocabulary with schema/control special tokens

---

🔧 What’s Changed

Added the following special tokens to the tokenizer:

- `<|domain_start|>`, `<|domain_end|>`
- `<|intent_start|>`, `<|intent_end|>`
- `<|slot_type_start|>`, `<|slot_type_end|>`
- `<|slot_span_start|>`, `<|slot_span_end|>`
- `<|canonical_start|>`, `<|canonical_end|>`

As a result: - Tokenizer vocabulary size is increased.

🎯 Intended Usage

This model is intended to be used as a base model for:

- schema-aware prompting
- structured information extraction
- slot / intent / domain prediction

All downstream LoRA adapters must be trained with the same tokenizer.

---

🚫 Compatibility Notes

- Vocabulary shapes are **fixed**
- Do NOT add or remove tokens at runtime
- Designed for **vLLM / TensorRT-LLM** serving
- Safe for multi-LoRA dynamic loading

---

📜 License

Apache-2.0 This model is a derivative work of Qwen/Qwen2.5-0.5B.