AvaSiG/argos-v1

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:May 15, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

AvaSiG/argos-v1 is a 1.5 billion parameter Qwen2.5-based instruction-tuned causal language model developed by AvaSiG. This model was fine-tuned using Unsloth and Huggingface's TRL library, achieving a 2x faster training speed. It is designed for general instruction-following tasks, leveraging its efficient training methodology.

Loading preview...

AvaSiG/argos-v1: Efficiently Fine-Tuned Qwen2.5-1.5B

AvaSiG/argos-v1 is a 1.5 billion parameter language model developed by AvaSiG, based on the Qwen2.5 architecture. This model distinguishes itself through its highly efficient fine-tuning process, which was accelerated by 2x using Unsloth in conjunction with Huggingface's TRL library. The base model for this fine-tuning was unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit.

Key Capabilities

  • Instruction Following: Designed to respond effectively to a wide range of user instructions.
  • Efficient Training: Leverages Unsloth for significantly faster fine-tuning, making it a practical choice for developers seeking quick iteration cycles.
  • Qwen2.5 Architecture: Benefits from the robust capabilities of the Qwen2.5 model family.

Good For

  • Applications requiring a compact yet capable instruction-tuned model.
  • Developers looking for models fine-tuned with efficient methods like Unsloth.
  • General-purpose text generation and understanding tasks where a 1.5B parameter model is suitable.