LLM
Llama 3.2 1B Synthia II Redmond GGUF
GGUF-quantized 1B parameter LLM finetuned on Synthia v1.5-II synthetic dataset with ChatML format, Apache-2.0 licensed.
About this model
This model is a GGUF quantization of the Llama 3.2 1B Synthia II Redmond model, originally finetuned by ArtificialGuyBR on the migtissera/Synthia-v1.5-II dataset. The base training uses synthetic data distillation from GPT-4, creating an instruct-tuned model with ChatML conversation format. It supports 8 languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. The GGUF format enables efficient CPU/GPU inference via llama.cpp, llama-cpp-python, or compatible runners. Licensed under Apache-2.0, it's suitable for both research and commercial use. The quantized version maintains the original model's capabilities while reducing memory footprint for deployment on consumer hardware.
Project signals
- 80 Hugging Face downloads
- 1 Hugging Face likes
Topics
transformers · gguf · instruct · finetune · chatml · gpt4 · synthetic data · distillation · facebook · meta