ligaments-dev/housing-qwen2.5-0.5b-sft
The ligaments-dev/housing-qwen2.5-0.5b-sft model is a 0.5 billion parameter causal language model, fine-tuned from Qwen/Qwen2.5-0.5B-Instruct. Developed by ligaments-dev, this model leverages a 32768 token context length and was trained using the TRL framework. It is optimized for specific conversational or generative tasks, building upon the base Qwen2.5 architecture.
Loading preview...
Model Overview
ligaments-dev/housing-qwen2.5-0.5b-sft is a 0.5 billion parameter language model, fine-tuned from the base Qwen/Qwen2.5-0.5B-Instruct model. This model was developed by ligaments-dev and utilizes a substantial context window of 32768 tokens, making it suitable for tasks requiring longer input sequences.
Training Details
The model underwent a supervised fine-tuning (SFT) process using the TRL library. This fine-tuning approach aims to adapt the pre-trained Qwen2.5 model to specific downstream applications or conversational styles. The training environment included:
- TRL: 1.5.1
- Transformers: 5.10.2
- Pytorch: 2.12.0
- Datasets: 5.0.0
- Tokenizers: 0.22.2
Usage
Developers can easily integrate this model into their projects using the Hugging Face transformers library. A quick start example demonstrates text generation, and standard AutoModelForCausalLM and AutoTokenizer classes can be used for loading the model and its tokenizer.