nibauman/ObjNav-Qwen3.5-4B-SFT-gemini

VISIONConcurrency Cost:1Model Size:4.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:May 7, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The nibauman/ObjNav-Qwen3.5-4B-SFT-gemini is a 4.5 billion parameter causal language model, fine-tuned by nibauman from the Qwen/Qwen3.5-4B base model. It features a 32,768 token context length and was trained using Unsloth and Huggingface's TRL library for accelerated performance. This model is optimized for specific tasks related to object navigation, leveraging its fine-tuned capabilities for enhanced performance in such applications.

Loading preview...

Model Overview

The nibauman/ObjNav-Qwen3.5-4B-SFT-gemini is a 4.5 billion parameter language model, fine-tuned by nibauman. It is based on the Qwen/Qwen3.5-4B architecture and features a substantial context length of 32,768 tokens, allowing it to process extensive inputs.

Key Characteristics

  • Base Model: Fine-tuned from Qwen/Qwen3.5-4B.
  • Parameter Count: 4.5 billion parameters.
  • Context Length: Supports a 32,768 token context window.
  • Training Efficiency: Training was accelerated by 2x using the Unsloth library in conjunction with Huggingface's TRL library.
  • License: Distributed under the Apache-2.0 license.

Potential Use Cases

This model is specifically fine-tuned, suggesting its optimization for particular tasks. While the exact nature of "ObjNav" is not detailed in the provided README, the naming implies potential applications in:

  • Object Navigation: Tasks requiring understanding and processing information related to object navigation.
  • Specialized Language Understanding: Scenarios where a model fine-tuned for specific domain knowledge, potentially related to object interaction or spatial reasoning, would be beneficial.

Developers looking for a Qwen3.5-4B variant with enhanced performance for specialized tasks, particularly those benefiting from accelerated fine-tuning methods, may find this model suitable.