ahmadfatikhulkhasan/qwen2.5-3b-legal-id-sft
The ahmadfatikhulkhasan/qwen2.5-3b-legal-id-sft is a 3.1 billion parameter Qwen2.5-based causal language model developed by ahmadfatikhulkhasan, fine-tuned from unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit. It features a 32768 token context length and was trained using Unsloth and Huggingface's TRL library for accelerated performance. This model is specifically optimized for legal tasks within the Indonesian context, leveraging its specialized fine-tuning.
Loading preview...
Model Overview
This model, ahmadfatikhulkhasan/qwen2.5-3b-legal-id-sft, is a 3.1 billion parameter Qwen2.5-based language model developed by ahmadfatikhulkhasan. It has been fine-tuned from the unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit base model, indicating an instruction-tuned foundation. The training process utilized Unsloth and Huggingface's TRL library, which enabled a 2x faster fine-tuning speed.
Key Characteristics
- Architecture: Qwen2.5-based, a causal language model.
- Parameter Count: 3.1 billion parameters.
- Context Length: Supports a substantial context window of 32768 tokens.
- Training Efficiency: Fine-tuned with Unsloth for accelerated training.
Primary Use Case
This model is specifically designed and fine-tuned for legal tasks within the Indonesian context. Its specialized training aims to enhance its performance and relevance for applications requiring understanding and generation of legal text in Indonesian.