zitaqiy/Llama-3.1-8B-Alpaca-Indo-GRPO
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Apr 8, 2026License:apache-2.0Architecture:Transformer Open Weights Cold
zitaqiy/Llama-3.1-8B-Alpaca-Indo-GRPO is an 8 billion parameter Llama-3.1 model developed by zitaqiy, fine-tuned from zitaqiy/Llama-3.1-8B-Alpaca-Indo-LR2e4. This model was trained using Unsloth and Huggingface's TRL library, enabling faster training. It is designed for general language tasks, leveraging its Llama-3.1 architecture and 32768 token context length.
Loading preview...
Model Overview
zitaqiy/Llama-3.1-8B-Alpaca-Indo-GRPO is an 8 billion parameter language model, fine-tuned by zitaqiy. It is based on the Llama-3.1 architecture and was specifically fine-tuned from the zitaqiy/Llama-3.1-8B-Alpaca-Indo-LR2e4 model. The training process utilized Unsloth and Huggingface's TRL library, which facilitated a 2x faster training speed.
Key Characteristics
- Architecture: Llama-3.1
- Parameter Count: 8 billion parameters
- Context Length: 32768 tokens
- Training Method: Fine-tuned using Unsloth and Huggingface's TRL library for accelerated training.
- License: Apache-2.0
Good for
- Applications requiring a Llama-3.1 based model with 8 billion parameters.
- Use cases where faster fine-tuning methods are beneficial.
- General language generation and understanding tasks, leveraging its substantial context window.