Instructions to use diffusion-reasoning/gdsd_code_llada with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use diffusion-reasoning/gdsd_code_llada with Transformers:

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

pipe = pipeline("text-generation", model="diffusion-reasoning/gdsd_code_llada", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("diffusion-reasoning/gdsd_code_llada", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use diffusion-reasoning/gdsd_code_llada with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "diffusion-reasoning/gdsd_code_llada"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "diffusion-reasoning/gdsd_code_llada",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/diffusion-reasoning/gdsd_code_llada

SGLang

How to use diffusion-reasoning/gdsd_code_llada 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 "diffusion-reasoning/gdsd_code_llada" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "diffusion-reasoning/gdsd_code_llada",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "diffusion-reasoning/gdsd_code_llada" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "diffusion-reasoning/gdsd_code_llada",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use diffusion-reasoning/gdsd_code_llada with Docker Model Runner:
```
docker model run hf.co/diffusion-reasoning/gdsd_code_llada
```

Add model card and metadata

by nielsr HF Staff - opened 4 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+32

-0

nielsr

4 days ago

This PR adds a model card for the GDSD model. It includes:

Metadata for the transformers library and text-generation pipeline.
A link to the paper: GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models.
A link to the official GitHub repository.
A citation section with the BibTeX from the paper.

Add model card and metadata4c1253a1

jky594176 changed pull request status to merged 1 day ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment