alamios/DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B

DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B

Updated to v1

This model is trained on CODE outputs of <a href="https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B">deepseek-ai/DeepSeek-R1-Distill-Qwen-32B</a> and is meant to be used only as draft model for speculative decoding.

It's specifically intended for users of 3090/4090, allowing you to run the DeepSeek-R1-Distill-Qwen-32B-Q4KM GGUF version with 16k context and speeding up generation without sacrificing more context length or model quality.

Data info

The data consists of code tasks collected from various datasets. It has been trained for 2 epochs on 2.5k unique examples, for a total of 7.6 million tokens per epoch.

Since data generation was done using spare GPU time, I may publish a further trained version later.