Downloads · 30 days
28
5% of all-time downloads
keisuke-miyako/Dream-v0-Instruct-7B-gguf-q4_k_m
Dream-v0-Instruct-7B-gguf-q4_k_m is a machine learning model from keisuke-miyako. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Dream is a new LLM developed by the HKU NLP Group. It uses the diffusion architecture typically used by image generation AI for text. In other words, instead of generation text sequentially, it gradually generates tex…
Downloads · 30 days
28
5% of all-time downloads
All-time downloads
606
Public
Repo size
4.7 GB
Likes
0
Public
Click a slice to open those files.
.gguf4.7 GB · 100%
From the Hugging Face model README
Dream is a new LLM developed by the HKU NLP Group. It uses the diffusion architecture typically used by image generation AI for text. In other words, instead of generation text sequentially, it gradually generates text in the style of "computer, enhance image!".
The Dream v0 Instruct 7B model is small enough to run locally on llama.cpp (4.68 GB in Q4_K_M quantisation).
llama.cpp added diffusion support around July 2025.
Demo with denoising process visualisation: https://huggingface.co/spaces/multimodalart/Dream
The specific CLI switches are only implemented in diffusion-cli, not llama-server which is designed to process autoregressive causal language models with a KV cache.