---
license: apache-2.0
language:
- en
base_model:
- alamios/DeepSeek-R1-DRAFT-Qwen2.5-0.5B
pipeline_tag: text-generation
library_name: transformers
tags:
- qwen
- qwen2.5
- deepseek
---

# DeepSeek-R1-DRAFT-Qwen2.5-0.5B-GGUF

This model is trained on 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-Q4_K_M GGUF version with 16k context and speeding up generation without sacrificing more context length or model quality.

# Data info

The data consists of code, math, reasoning and general knowledge tasks collected from various datasets. It has been trained for 4 epochs on 5200 unique examples, for a total of 21,600,000 tokens per epoch.

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