Model Overview

CreitinGameplays/Llama-3.1-8B-R1-v0.1 is an 8 billion parameter language model based on the Llama 3.1 architecture. It was fine-tuned by CreitinGameplays over a period of 28 hours using two Nvidia RTX A6000 GPUs. The training involved 2 epochs with a batch size of 8, a learning rate of 1e-4, and a warmup ratio of 0.1.

Key Capabilities

• Conversational AI: Designed to function as an AI assistant, capable of engaging in chat sessions and generating responses based on user input and system prompts.
• Extended Context Window: Supports a context length of 32768 tokens, allowing for more extensive and detailed conversations.
• Quantization Support: The provided example code demonstrates loading the model with 8-bit quantization, enabling more efficient memory usage.

Current Limitations

• The model may occasionally fail to output the complete final response after its internal reasoning process.

Good For

• Developers looking for a fine-tuned Llama 3.1 variant for chat applications.
• Experimentation with conversational AI models that support 8-bit quantization.
• Use cases requiring a model with a substantial context window for maintaining long dialogue histories.