Hyeongwon/P2-split4_prob_Llama-3.2-3B-Base_0524-1

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:3.2BQuant:BF16Ctx Length:32kPublished:May 24, 2026Architecture:Transformer Warm

Hyeongwon/P2-split4_prob_Llama-3.2-3B-Base_0524-1 is a 3.2 billion parameter language model, fine-tuned from Meta's Llama-3.2-3B architecture. This model was trained using Supervised Fine-Tuning (SFT) with the TRL library. It is designed for general text generation tasks, leveraging its Llama-3.2 base for broad language understanding and generation capabilities.

Loading preview...

Model Overview

Hyeongwon/P2-split4_prob_Llama-3.2-3B-Base_0524-1 is a 3.2 billion parameter language model, building upon the foundational Meta Llama-3.2-3B architecture. This model has undergone Supervised Fine-Tuning (SFT) using the Hugging Face TRL library, indicating a focus on adapting its base capabilities to specific tasks or improving its instruction following.

Key Characteristics

  • Base Model: Fine-tuned from meta-llama/Llama-3.2-3B.
  • Training Method: Utilizes Supervised Fine-Tuning (SFT) for specialized performance.
  • Framework: Trained with the TRL (Transformer Reinforcement Learning) library, version 0.25.1.
  • Parameter Count: A compact 3.2 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: Supports a substantial context window of 32,768 tokens.

Intended Use Cases

This model is suitable for a variety of text generation tasks where a Llama-3.2-3B base model, enhanced through SFT, would be beneficial. Its moderate size makes it a good candidate for applications requiring efficient inference while still delivering robust language understanding and generation. Developers can leverage it for tasks such as:

  • General question answering.
  • Creative content generation.
  • Summarization.
  • Dialogue systems.