LLM
Qwen 2 1.5B Synthia II Redmond GGUF
GGUF quantized version of Qwen 2 1.5B fine-tuned on Synthia v1.5-II synthetic GPT-4 data for chat in ChatML format.
About this model
This model is a GGUF quantization of Qwen 2 1.5B Synthia II Redmond, a 1.5-billion-parameter language model fine-tuned on the Synthia v1.5-II dataset by migtissera. The Synthia dataset consists of synthetic conversations generated by GPT-4, distilled into a format suitable for training smaller models. The original instruct model uses the ChatML prompt format and is licensed under Apache 2.0. This GGUF version makes the fine-tune runnable in llama.cpp-compatible runtimes on CPU or GPU, so it can be deployed locally without a dedicated inference server.
The model was quantized by ArtificialGuyBR with GPU sponsorship from Redmond.AI, and the base instruct model is available as artificialguybr/QWEN-2-1.5B-Synthia-II-Redmond. The model card points to TheBloke's GGUF guides for details on loading the file, including how to concatenate multi-part GGUF files if needed. At 1.5B parameters it is a lightweight conversational model, well suited to local chat applications, prototyping, or endpoints where a small fast instruct model is preferred. Tags on the model card confirm it is endpoints_compatible and conversational.
Learn more
Read the in-depth guide about Qwen 2 1.5B Synthia II Redmond GGUF
Project signals
- 157 Hugging Face downloads
- 4 Hugging Face likes
Topics
transformers · gguf · instruct · finetune · chatml · gpt4 · synthetic data · distillation · dataset:migtissera/synthia-v1.5-ii · endpoints_compatible