corn6/DeepSeek-R1-Chinese-Law

TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Apr 3, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

The corn6/DeepSeek-R1-Chinese-Law is an 8 billion parameter language model developed by corn6, fine-tuned from unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is specifically designed for applications requiring a Chinese law-focused language model.

Loading preview...

Model Overview

The corn6/DeepSeek-R1-Chinese-Law is an 8 billion parameter language model developed by corn6. It is fine-tuned from the unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit base model, leveraging the Unsloth library for accelerated training. This optimization allowed for a 2x faster training process, utilizing Huggingface's TRL library.

Key Capabilities

  • Specialized Domain: Focused on the Chinese law domain, suggesting enhanced performance for legal texts and queries in Chinese.
  • Efficient Training: Benefits from Unsloth's optimizations, leading to faster fine-tuning.
  • Llama Architecture: Built upon a Llama-based architecture, providing a robust foundation.

Good For

  • Applications requiring a language model with expertise in Chinese legal contexts.
  • Developers looking for an efficiently trained model for specialized tasks.
  • Research and development in legal AI for the Chinese market.