lugman-madhiai/Qwen3.5-2B-SearchAgent-SFT-01

VISIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2.3BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 11, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

The lugman-madhiai/Qwen3.5-2B-SearchAgent-SFT-01 is a 2.3 billion parameter Qwen3.5-based causal language model, fine-tuned by lugman-madhiai. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for search agent applications, leveraging its fine-tuned capabilities within a 32768 token context length.

Loading preview...

Model Overview

The lugman-madhiai/Qwen3.5-2B-SearchAgent-SFT-01 is a 2.3 billion parameter language model, fine-tuned from the Qwen/Qwen3.5-2B base model. Developed by lugman-madhiai, this model is specifically optimized for search agent functionalities.

Key Characteristics

  • Base Model: Qwen/Qwen3.5-2B architecture.
  • Parameter Count: 2.3 billion parameters.
  • Context Length: Supports a substantial context window of 32768 tokens.
  • Training Efficiency: Fine-tuned using Unsloth and Huggingface's TRL library, resulting in a 2x speedup during training.
  • License: Distributed under the Apache-2.0 license.

Use Cases

This model is particularly well-suited for applications requiring a specialized search agent. Its fine-tuned nature suggests enhanced performance in tasks related to information retrieval, query understanding, and agent-based interactions within a search context. The efficient training process indicates a focus on practical deployment and performance.