Instructions to use inclusionAI/LLaDA2.1-flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inclusionAI/LLaDA2.1-flash with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/LLaDA2.1-flash", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("inclusionAI/LLaDA2.1-flash", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inclusionAI/LLaDA2.1-flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inclusionAI/LLaDA2.1-flash"
# 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/LLaDA2.1-flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inclusionAI/LLaDA2.1-flash

SGLang

How to use inclusionAI/LLaDA2.1-flash 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/LLaDA2.1-flash" \
    --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/LLaDA2.1-flash",
		"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/LLaDA2.1-flash" \
        --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/LLaDA2.1-flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inclusionAI/LLaDA2.1-flash with Docker Model Runner:
```
docker model run hf.co/inclusionAI/LLaDA2.1-flash
```

LLaDA2.1-flash

Commit History

Nov 2 9 days ago

14:20
Add community evaluation results for MMLU-Pro⁠

nielsr HF Staff

Verified signature
7d021a7

Apr 13

11:45
fix: align RotaryEmbedding with Qwen2Moe pattern for transformers compat (#4)⁠

lccurious +1: kashif

2bf95e8
11:27
Insert tracking points on the ModelCard to track visit statistics (#5)⁠

xiaoyayaya

817271e

Mar 16

13:55
Update README.md

utdawn

Verified signature
823c707

Feb 12

16:23
Update README.md

utdawn

Verified signature
408f916

Feb 10

03:47
Update README.md

utdawn

Verified signature
afa23bf

Feb 9

17:38
Update modeling_llada2_moe.py

utdawn

Verified signature
bb290a9
17:30
Update README.md

utdawn

Verified signature
c538cf1
17:23
Create modeling_llada2_moe.py

utdawn

Verified signature
c54780e
17:22
Update configuration_llada2_moe.py

utdawn

Verified signature
d439464
17:16
Create README.md

utdawn

Verified signature
e763a7e
14:49
Add files using upload-large-folder tool

m1ngcheng

Verified signature
849c58d
10:47
initial commit

m1ngcheng

Verified signature
fbe251b

Commit History

Nov 2 9 days ago

Add community evaluation results for MMLU-Pro⁠

Apr 13

fix: align RotaryEmbedding with Qwen2Moe pattern for transformers compat (#4)⁠

Insert tracking points on the ModelCard to track visit statistics (#5)⁠

Mar 16

Update README.md

Feb 12

Update README.md

Feb 10

Update README.md

Feb 9

Update modeling_llada2_moe.py

Update README.md

Create modeling_llada2_moe.py

Update configuration_llada2_moe.py

Create README.md

Add files using upload-large-folder tool

initial commit