Hugging Face's logo

z-lab
/
LLaMA3.1-8B-Instruct-DFlash-UltraChat

Text Generation
Transformers
Safetensors
qwen3
feature-extraction
dflash
speculative-decoding
diffusion
efficiency
flash-decoding
qwen
diffusion-language-model
custom_code
text-generation-inference
Model card Files
xet
 Community
jianchen0311 commited on
Commit
6c95c73
·
verified ·
1 Parent(s): c0a62a1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -12,7 +12,7 @@ tags:
12
  ---
13
 
14
  # LLaMA3.1-8B-Instruct-DFlash-UltraChat
15
- [**Paper (Coming Soon)**](#) | [**GitHub**](https://github.com/z-lab/dflash) | [**Blog**](https://z-lab.ai/projects/dflash/)
16
 
17
  **DFlash** is a novel speculative decoding method that utilizes a lightweight **block diffusion** model for drafting. It enables efficient, high-quality parallel drafting that pushes the limits of inference speed.
18
 
 
12
  ---
13
 
14
  # LLaMA3.1-8B-Instruct-DFlash-UltraChat
15
+ [**Paper**](https://arxiv.org/abs/2602.06036) | [**GitHub**](https://github.com/z-lab/dflash) | [**Blog**](https://z-lab.ai/projects/dflash/)
16
 
17
  **DFlash** is a novel speculative decoding method that utilizes a lightweight **block diffusion** model for drafting. It enables efficient, high-quality parallel drafting that pushes the limits of inference speed.
18