deartheiz/LLM-LuatGiaoThong

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kPublished:Apr 28, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

LLM-LuatGiaoThong is an 8 billion parameter Llama 3.1-based causal language model developed by deartheiz, fine-tuned using Unsloth and Huggingface's TRL library. This model is optimized for specific tasks related to its fine-tuning data, offering efficient performance due to its training methodology. It leverages the Llama 3.1 architecture for general language understanding and generation, with a context length of 8192 tokens.

Loading preview...

Model Overview

LLM-LuatGiaoThong is an 8 billion parameter language model developed by deartheiz. It is built upon the Llama 3.1 architecture and has been fine-tuned from the unsloth/llama-3.1-8b-bnb-4bit base model. The fine-tuning process utilized the Unsloth library, which enabled a 2x faster training speed, alongside Huggingface's TRL library.

Key Characteristics

  • Base Model: Llama 3.1-8B
  • Parameters: 8 billion
  • Context Length: 8192 tokens
  • Training Method: Fine-tuned using Unsloth and Huggingface TRL for accelerated training.
  • License: Apache-2.0

Intended Use

This model is designed for applications that can benefit from a Llama 3.1-based model fine-tuned with efficient methods. Its specific fine-tuning data, implied by its name "LuatGiaoThong" (Traffic Law), suggests potential specialization in areas related to traffic regulations or similar domain-specific knowledge. Developers can leverage its Llama 3.1 foundation for general language tasks while benefiting from its specialized fine-tuning for relevant use cases.