mneb/qwen2.5-7b-finerweb
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:May 30, 2026Architecture:Transformer Warm
The mneb/qwen2.5-7b-finerweb model is a 7.6 billion parameter Qwen2.5-7B-Instruct variant, fine-tuned specifically for XML-based Named Entity Recognition (NER). It excels at identifying and tagging named entities within text using user-defined labels, wrapping them in XML-style tags. This model is optimized for precise, in-context entity extraction without altering the original text, making it suitable for structured data annotation tasks.
Loading preview...
Overview
The mneb/qwen2.5-7b-finerweb model is a specialized 7.6 billion parameter variant of the Qwen2.5-7B-Instruct architecture. It has been fine-tuned to perform XML-based Named Entity Recognition (NER), allowing users to extract and tag specific entities within text.
Key Capabilities
- XML-style Tagging: Wraps detected entities in user-defined XML tags.
- Customizable Labels: Supports a user-defined set of entity labels for flexible NER tasks.
- Preserves Original Text: Designed to insert tags without altering, rewriting, or translating the input text.
- Lightweight Inference: Provides a straightforward inference script for easy integration.
Good For
- Structured Data Annotation: Ideal for tasks requiring the extraction and tagging of specific information into a structured, XML-like format.
- Information Extraction: Useful for identifying persons, locations, organizations, or other custom entities from unstructured text.
- Research and Development: Provides a fine-tuned base for further experimentation in NER and text processing applications.