AshutoshSingh08/aditi-assistant-merged

TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kTool Calling:SupportedPublished:Jun 1, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

AshutoshSingh08/aditi-assistant-merged is an 8 billion parameter instruction-tuned causal language model developed by AshutoshSingh08. This model is finetuned from unsloth/Meta-Llama-3.1-8B-bnb-4bit and was trained 2x faster using Unsloth and Huggingface's TRL library. It is designed for general assistant-like tasks, leveraging its Llama 3.1 base for robust language understanding and generation.

Loading preview...

Model Overview

AshutoshSingh08/aditi-assistant-merged is an 8 billion parameter instruction-tuned language model, developed by AshutoshSingh08. It is built upon the unsloth/Meta-Llama-3.1-8B-bnb-4bit base model, indicating a strong foundation in the Llama 3.1 architecture.

Key Characteristics

  • Base Model: Finetuned from unsloth/Meta-Llama-3.1-8B-bnb-4bit, providing a robust and capable starting point.
  • Training Efficiency: The model was trained with significant speed improvements, achieving 2x faster training times by utilizing Unsloth and Huggingface's TRL library. This suggests an optimized training process.
  • License: Distributed under the permissive Apache-2.0 license, allowing for broad use and modification.

Potential Use Cases

Given its instruction-tuned nature and Llama 3.1 base, this model is well-suited for a variety of general-purpose assistant applications, including:

  • Conversational AI: Engaging in dialogue and answering user queries.
  • Text Generation: Creating coherent and contextually relevant text for various prompts.
  • Instruction Following: Executing tasks based on explicit instructions.

Finetunes
1 models