kartik4w87y7/riya-ai-v2
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kPublished:May 26, 2026License:apache-2.0Architecture:Transformer Open Weights Warm
Riya-AI-v2 is an 8 billion parameter instruction-tuned Llama 3.1 model developed by kartik4w87y7. This model was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training. It is designed for general-purpose conversational AI tasks, leveraging the Llama 3.1 architecture for robust performance.
Loading preview...
Overview
Riya-AI-v2 is an 8 billion parameter instruction-tuned language model developed by kartik4w87y7. It is based on the unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit model, leveraging the Llama 3.1 architecture. This model was fine-tuned using the Unsloth library in conjunction with Huggingface's TRL library, which facilitated a 2x faster training process.
Key Capabilities
- Instruction Following: Designed to understand and execute instructions effectively due to its instruction-tuned nature.
- Llama 3.1 Foundation: Benefits from the advanced capabilities and performance characteristics of the Meta-Llama-3.1-8B-Instruct base model.
- Efficient Training: Utilizes Unsloth for optimized and accelerated fine-tuning.
Good For
- General Conversational AI: Suitable for a wide range of dialogue-based applications.
- Rapid Prototyping: The efficient training process suggests it could be a good candidate for projects requiring quick iteration on fine-tuned models.
- Llama 3.1 Ecosystem: Ideal for developers already working within the Llama 3.1 framework who need an instruction-tuned variant.