culexx/qwen3-1.7b-legal-sft

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 27, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The culexx/qwen3-1.7b-legal-sft is a 1.7 billion parameter Qwen3 model developed by culexx, fine-tuned for legal applications. This model was optimized for faster training using Unsloth and Huggingface's TRL library, making it efficient for specialized domain adaptation. It is designed to excel in tasks requiring legal domain understanding and generation, leveraging its specialized fine-tuning.

Loading preview...

Model Overview

The culexx/qwen3-1.7b-legal-sft is a specialized Qwen3 model with 1.7 billion parameters, developed by culexx. It has been fine-tuned specifically for legal applications, building upon the unsloth/Qwen3-1.7B-Base-unsloth-bnb-4bit base model.

Key Characteristics

  • Legal Domain Specialization: This model is explicitly fine-tuned for tasks within the legal domain, suggesting enhanced performance and relevance for legal text processing.
  • Efficient Training: The fine-tuning process leveraged Unsloth and Huggingface's TRL library, enabling a 2x faster training speed. This indicates an efficient approach to domain adaptation.
  • Qwen3 Architecture: Based on the Qwen3 architecture, it benefits from the foundational capabilities of this model family.

Use Cases

This model is particularly well-suited for applications requiring a deep understanding and generation of legal text. Potential use cases include:

  • Legal document analysis
  • Legal research assistance
  • Generating legal summaries or drafts
  • Question answering in a legal context

Finetunes
1 models