LLM
Qwen 2.5 0.5B Synthia I GGUF
GGUF quantized version of Qwen 2.5 0.5B fine-tuned on Synthia v1.5 synthetic dataset for instruction following.
About this model
This model is a GGUF quantized release of Qwen 2.5 0.5B Synthia I, a 0.5B parameter language model fine-tuned on the Synthia v1.5 dataset by migtissera. The Synthia dataset consists of synthetic data generated by GPT-4 for instruction tuning and distillation. The base model (artificialguybr/QWEN-2.5-0.5B-Synthia-I) was trained using ChatML format and is optimized for conversational use. This GGUF version enables efficient CPU inference via llama.cpp and compatible runtimes. Licensed under Apache-2.0.
Project signals
- 240 Hugging Face downloads
- 3 Hugging Face likes
Topics
transformers · gguf · instruct · finetune · chatml · gpt4 · synthetic data · distillation · dataset:migtissera/synthia-v1.5-i · endpoints_compatible