idkwhyitsnotworking/Kagura-Llama-3.1-8B-Instruct
TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jun 19, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold
Kagura-Llama-3.1-8B-Instruct is an 8 billion parameter instruction-tuned causal language model developed by idkwhyitsnotworking. This model is finetuned from Meta Llama 3.1 and optimized for performance, having been trained 2x faster using Unsloth and Huggingface's TRL library. It offers a 32768 token context length and is designed for general instruction-following tasks.
Loading preview...
Kagura-Llama-3.1-8B-Instruct Overview
Kagura-Llama-3.1-8B-Instruct is an 8 billion parameter instruction-tuned language model developed by idkwhyitsnotworking. It is built upon the Meta Llama 3.1 architecture and features a substantial 32768 token context window, making it suitable for processing longer inputs and generating comprehensive responses.
Key Characteristics
- Base Model: Finetuned from
unsloth/meta-llama-3.1-8b-instruct-unsloth-bnb-4bit. - Training Efficiency: The model was trained with significant speed improvements, achieving 2x faster training times by leveraging the Unsloth library in conjunction with Huggingface's TRL library.
- Instruction Following: Optimized for understanding and executing a wide range of instructions, making it versatile for various NLP applications.
Good For
- General Instruction-Following: Excels at tasks requiring adherence to specific prompts and instructions.
- Applications requiring efficient training: Demonstrates the benefits of using Unsloth for faster fine-tuning of large language models.
- Developers seeking a Llama 3.1-based model: Offers a performant option within the Llama 3.1 ecosystem.