Kerassy/qwen-2.5-3b-smoltalk-sft

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 16, 2026Architecture:Transformer Featherless Exclusive Cold

Kerassy/qwen-2.5-3b-smoltalk-sft is a 3.1 billion parameter instruction-tuned causal language model based on Qwen/Qwen2.5-3B, developed by Kerassy. Fine-tuned on the HuggingFaceTB/smoltalk dataset, it specializes in generating everyday conversations. This model is optimized for conversational AI tasks, offering a compact solution for dialogue generation.

Loading preview...

Model Overview

Kerassy/qwen-2.5-3b-smoltalk-sft is an instruction-tuned variant of the 3.1 billion parameter Qwen/Qwen2.5-3B base model. It has been fine-tuned using Supervised Fine-Tuning (SFT) with Low-Rank Adaptation (LoRA) on the everyday-conversations subset of the HuggingFaceTB/smoltalk dataset.

Key Capabilities

  • Conversational AI: Specialized in generating natural, everyday dialogue.
  • Compact Size: At 3.1 billion parameters, it offers a balance between performance and computational efficiency.
  • Qwen2.5 Architecture: Leverages the robust architecture of the Qwen2.5 series.

Good For

  • Dialogue Generation: Ideal for applications requiring realistic conversational responses.
  • Chatbots: Suitable for building chatbots focused on general conversation.
  • Resource-Constrained Environments: Its smaller size makes it viable for deployment on hardware with limited resources, such as a single NVIDIA L4 GPU.