Instructions to use SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora

SGLang

How to use SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora with Docker Model Runner:
```
docker model run hf.co/SJTU-DENG-Lab/D2F_Dream_Base_7B_Lora
```

UnhurriedDawn commited on Aug 14, 2025

Commit

2e33caa

verified ·

1 Parent(s): bc9e033

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ This repository contains the **LoRA adapter** for the `Dream-org/Dream-v0-Instru
 This adapter allows the `Dream-Base-7B` diffusion LLM (dLLM) to achieve inference speeds that are significantly faster than both its original version and leading autoregressive (AR) models like LLaMA3, while maintaining comparable output quality.
-The D2F method and its results are detailed in the paper: **[D2F: Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing](https://github.com/zhijie-group/Discrete-Diffusion-Forcing/blob/main/Discrete%20Diffusion%20Forcing.pdf)**.
 - **Official Code:** [D2F GitHub Repository](https://github.com/zhijie-group/Discrete-Diffusion-Forcing)
 - **Demo Space:** [D2F-LLaDA-Instruct-8B](https://huggingface.co/spaces/zhijie3/D2F-LLaDA-Instruct-8B)

 This adapter allows the `Dream-Base-7B` diffusion LLM (dLLM) to achieve inference speeds that are significantly faster than both its original version and leading autoregressive (AR) models like LLaMA3, while maintaining comparable output quality.
+The D2F method and its results are detailed in the paper: **[D2F: Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing](https://arxiv.org/abs/2508.09192)**.
 - **Official Code:** [D2F GitHub Repository](https://github.com/zhijie-group/Discrete-Diffusion-Forcing)
 - **Demo Space:** [D2F-LLaDA-Instruct-8B](https://huggingface.co/spaces/zhijie3/D2F-LLaDA-Instruct-8B)