wls04/Qwen2.5-14B-AcaciaWL-Add
The wls04/Qwen2.5-14B-AcaciaWL-Add model is a fine-tuned version of the Qwen/Qwen2.5-14B-Instruct architecture, featuring 14.8 billion parameters and a 32768-token context length. This model has been specifically trained using Supervised Fine-Tuning (SFT) with the TRL framework. It is designed to enhance the base Qwen2.5-14B-Instruct model's capabilities through targeted training, making it suitable for general language generation and instruction-following tasks.
Loading preview...
Model Overview
This model, wls04/Qwen2.5-14B-AcaciaWL-Add, is a specialized fine-tuned variant of the robust Qwen/Qwen2.5-14B-Instruct base model. Leveraging the TRL (Transformer Reinforcement Learning) framework, it has undergone Supervised Fine-Tuning (SFT) to refine its performance and instruction-following abilities. With 14.8 billion parameters and a substantial 32768-token context window, it builds upon the strong foundation of the Qwen2.5 series.
Key Capabilities
- Enhanced Instruction Following: Benefits from SFT to better understand and execute user instructions.
- General Text Generation: Capable of generating coherent and contextually relevant text for a wide range of prompts.
- Large Context Window: Supports processing and generating content based on long input sequences, up to 32768 tokens.
Training Details
The model was trained using the SFT method within the TRL framework, specifically utilizing TRL version 0.27.1, Transformers 4.57.6, Pytorch 2.9.0, Datasets 4.0.0, and Tokenizers 0.22.2. This targeted training aims to improve its overall utility and responsiveness in conversational and generative AI applications.