angelinahung/finetuned-llama3-bahasa
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kPublished:May 19, 2026License:apache-2.0Architecture:Transformer Open Weights Warm
The angelinahung/finetuned-llama3-bahasa model is an 8 billion parameter Llama 3-based language model developed by angelinahung. It was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training. This model is specifically adapted for Bahasa, making it suitable for applications requiring Indonesian language understanding and generation.
Loading preview...
Model Overview
This model, angelinahung/finetuned-llama3-bahasa, is an 8 billion parameter language model based on the Llama 3 architecture. It was developed by angelinahung and fine-tuned using the Unsloth library in conjunction with Huggingface's TRL library, which facilitated a 2x faster training process.
Key Characteristics
- Base Model: Llama 3 (8B parameters)
- Training Efficiency: Utilizes Unsloth for accelerated fine-tuning.
- Language Focus: Specifically adapted for Bahasa, indicating its primary utility for Indonesian language tasks.
- License: Distributed under the Apache-2.0 license.
Use Cases
This model is particularly well-suited for applications requiring:
- Bahasa Language Processing: Tasks such as text generation, summarization, translation, or question answering in Indonesian.
- Efficient Deployment: Its fine-tuning with Unsloth suggests potential for optimized performance and resource usage compared to standard fine-tuning methods for Llama 3 models of similar size.