Instructions to use inclusionAI/LLaDA-MoE-7B-A1B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inclusionAI/LLaDA-MoE-7B-A1B-Base with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/LLaDA-MoE-7B-A1B-Base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("inclusionAI/LLaDA-MoE-7B-A1B-Base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inclusionAI/LLaDA-MoE-7B-A1B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inclusionAI/LLaDA-MoE-7B-A1B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inclusionAI/LLaDA-MoE-7B-A1B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inclusionAI/LLaDA-MoE-7B-A1B-Base

SGLang

How to use inclusionAI/LLaDA-MoE-7B-A1B-Base 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 "inclusionAI/LLaDA-MoE-7B-A1B-Base" \
    --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": "inclusionAI/LLaDA-MoE-7B-A1B-Base",
		"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 "inclusionAI/LLaDA-MoE-7B-A1B-Base" \
        --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": "inclusionAI/LLaDA-MoE-7B-A1B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inclusionAI/LLaDA-MoE-7B-A1B-Base with Docker Model Runner:
```
docker model run hf.co/inclusionAI/LLaDA-MoE-7B-A1B-Base
```

Improve model card with paper, code, project links and pipeline tag

by nielsr HF Staff - opened Oct 21, 2025

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-5

Files changed (1) hide show

README.md +9 -5

README.md CHANGED Viewed

@@ -1,14 +1,22 @@
 ---
 license: apache-2.0
 tags:
 - dllm
 - diffusion
 - llm
 - text_generation
-library_name: transformers
 ---
 # LLaDA-MoE
 **LLaDA-MoE** is a new and upgraded series of the LLaDA diffusion language model. This pre-release includes two cutting-edge models:
 - `LLaDA-MoE-7B-A1B-Base`: A base pre-trained model designed for research and secondary development.
@@ -223,10 +231,6 @@ input_ids = torch.tensor(input_ids).to(device).unsqueeze(0)
 text = generate(model, input_ids, steps=128, gen_length=128, block_length=32, temperature=0., cfg_scale=0., remasking='low_confidence')
 print(tokenizer.batch_decode(text[:, input_ids.shape[1]:], skip_special_tokens=False)[0])
 ```

 ---
+library_name: transformers
 license: apache-2.0
 tags:
 - dllm
 - diffusion
 - llm
 - text_generation
+pipeline_tag: text-generation
 ---
 # LLaDA-MoE
+This model is based on the principles described in the paper [Large Language Diffusion Models](https://huggingface.co/papers/2502.09992).
+- 📚 [Paper](https://huggingface.co/papers/2502.09992)
+- 🏠 [Project Page](https://ml-gsai.github.io/LLaDA-demo/)
+- 💻 [Code](https://github.com/ML-GSAI/LLaDA)
 **LLaDA-MoE** is a new and upgraded series of the LLaDA diffusion language model. This pre-release includes two cutting-edge models:
 - `LLaDA-MoE-7B-A1B-Base`: A base pre-trained model designed for research and secondary development.
 text = generate(model, input_ids, steps=128, gen_length=128, block_length=32, temperature=0., cfg_scale=0., remasking='low_confidence')
 print(tokenizer.batch_decode(text[:, input_ids.shape[1]:], skip_special_tokens=False)[0])
 ```