lakshyaixi/Llama_3_2_3B_Conversational_v7_SFT_10voicebot_loopcleaned

TEXT GENERATIONConcurrency Cost:1Model Size:3.2BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 25, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

lakshyaixi/Llama_3_2_3B_Conversational_v7_SFT_10voicebot_loopcleaned is a 3.2 billion parameter Llama 3.2-based conversational model developed by lakshyaixi. Finetuned from unsloth/Llama-3.2-3B-Instruct, this model was trained using Unsloth and Huggingface's TRL library for accelerated performance. It is optimized for conversational AI applications, leveraging its efficient training methodology to provide a capable language model.

Loading preview...

Overview

This model, lakshyaixi/Llama_3_2_3B_Conversational_v7_SFT_10voicebot_loopcleaned, is a 3.2 billion parameter conversational language model developed by lakshyaixi. It is finetuned from the unsloth/Llama-3.2-3B-Instruct base model, indicating its foundation in the Llama 3.2 architecture.

Key Characteristics

  • Base Model: Finetuned from unsloth/Llama-3.2-3B-Instruct.
  • Parameter Count: Features 3.2 billion parameters, offering a balance between performance and computational efficiency.
  • Training Efficiency: The model was trained using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.

Intended Use Cases

This model is designed for conversational AI applications, benefiting from its instruction-tuned base and efficient finetuning. Its optimized training makes it suitable for scenarios where rapid deployment and good conversational capabilities are required, particularly within the 3 billion parameter class.

Finetunes
1 models