dinhxuanhuy/Qwen2.5-3B-PhoMT-500kMulti

TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 22, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

dinhxuanhuy/Qwen2.5-3B-PhoMT-500kMulti is a 3.1 billion parameter Qwen2.5 model developed by dinhxuanhuy. This model is a finetuned variant of dinhxuanhuy/Qwen2.5-3B-PhoMT-250k, optimized using Unsloth and Huggingface's TRL library for faster training. It features a 32768 token context length and is designed for specific applications based on its finetuning.

Loading preview...

Model Overview

dinhxuanhuy/Qwen2.5-3B-PhoMT-500kMulti is a 3.1 billion parameter language model based on the Qwen2.5 architecture. Developed by dinhxuanhuy, this model is a finetuned version of the previously released dinhxuanhuy/Qwen2.5-3B-PhoMT-250k.

Key Characteristics

  • Architecture: Qwen2.5-3B, indicating a 3.1 billion parameter model.
  • Training Optimization: The model was finetuned using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.
  • Context Length: It supports a context window of 32768 tokens.
  • License: The model is released under the Apache-2.0 license.

Intended Use

This model is a specialized finetune, likely intended for tasks related to its base model's capabilities, with potential improvements in efficiency due to the optimized training methodology. Developers looking for a Qwen2.5-based model with efficient finetuning should consider this variant.

Finetunes
1 models