wombatapp/dicoding-law
The wombatapp/dicoding-law model is an 8 billion parameter Llama 3-based instruction-tuned language model developed by wombatapp. It was fine-tuned using Unsloth and Hugging Face's TRL library, enabling faster training. This model is designed for general instruction-following tasks, leveraging its Llama 3 foundation and efficient fine-tuning process.
Loading preview...
Model Overview
The wombatapp/dicoding-law is an 8 billion parameter instruction-tuned language model developed by wombatapp. It is built upon the Llama 3 architecture, specifically fine-tuned from unsloth/llama-3-8b-Instruct-bnb-4bit.
Key Characteristics
- Base Model: Fine-tuned from Llama 3 8B Instruct.
- Training Efficiency: The model was trained significantly faster using the Unsloth library in conjunction with Hugging Face's TRL library.
- Context Length: It supports a context length of 8192 tokens.
- License: Distributed under the Apache-2.0 license.
Use Cases
This model is suitable for general instruction-following applications where a Llama 3-based model with efficient fine-tuning is beneficial. Its 8 billion parameters make it a capable choice for various natural language understanding and generation tasks.