NOTE: See here for update on the version with ~3B tokens of fine-tuning applied.

A 0.5B parameter draft model for speculative sampling for use with deepseek-ai/DeepSeek-R1 created from alamios/DeepSeek-R1-DRAFT-Qwen2.5-0.5B using transplant-vocab.

NOTE: This is a draft model for the full-sized DeepSeek-R1 model and not the smaller "distilled" models!

GGUF

Model size

590M params

Architecture

qwen2

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jukofyork/DeepSeek-R1-DRAFT-0.5B-GGUF

Base model

Finetuned

Quantized

(105)

this model

Collection including jukofyork/DeepSeek-R1-DRAFT-0.5B-GGUF