yonommy0328/ConnectAI-basic-v2

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 28, 2026Architecture:Transformer Featherless Exclusive Cold

ConnectAI-basic-v2 by yonommy0328 is a 3.1 billion parameter instruction-tuned model, based on the Qwen2.5-3B-Instruct architecture. This model has been fine-tuned and converted to GGUF format using Unsloth, offering efficient deployment. It is designed for general language tasks and is optimized for use with `llama-cli` and `llama-mtmd-cli`.

Loading preview...

ConnectAI-basic-v2 Overview

ConnectAI-basic-v2 is an instruction-tuned language model, specifically the Qwen2.5-3B-Instruct architecture, developed by yonommy0328. This 3.1 billion parameter model has been optimized for efficient deployment and usage through its conversion to the GGUF format.

Key Characteristics

  • Architecture: Based on Qwen2.5-3B-Instruct.
  • Parameter Count: 3.1 billion parameters.
  • Format: Provided in GGUF format, enabling compatibility with various inference engines.
  • Optimization: Fine-tuned and converted using Unsloth, which facilitates faster training and deployment.
  • Context Length: Supports a context length of 32768 tokens.

Usage and Deployment

This model is designed for straightforward integration into command-line interfaces. It includes an Ollama Modelfile for easy deployment with Ollama. Users can interact with the model using llama-cli for text-only applications or llama-mtmd-cli for multimodal scenarios, leveraging its GGUF format for efficient execution.

Finetunes
1 models