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

Libraries

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

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

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

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("inclusionAI/LLaDA2.1-mini", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

error report to run example

by cloudyu - opened Feb 11

Discussion

cloudyu

Feb 11

test_llada21.py", line 7, in
model = AutoModelForCausalLM.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.12/site-packages/transformers/models/auto/auto_factory.py", line 367, in from_pretrained
return model_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.12/site-packages/transformers/modeling_utils.py", line 4021, in from_pretrained
model = cls(config, *model_args, **model_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/.cache/huggingface/modules/transformers_modules/LLaDA2_dot_1_hyphen_mini/modeling_llada2_moe.py", line 962, in init
self.model = LLaDA2MoeModel(config)
^^^^^^^^^^^^^^^^^^^^^^
File "/Users/.cache/huggingface/modules/transformers_modules/LLaDA2_dot_1_hyphen_mini/modeling_llada2_moe.py", line 783, in init
self.rotary_emb = LLaDA2MoeRotaryEmbedding(config=config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/.cache/huggingface/modules/transformers_modules/LLaDA2_dot_1_hyphen_mini/modeling_llada2_moe.py", line 108, in init
self.rope_init_fn = ROPE_INIT_FUNCTIONS[self.rope_type]
~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^
KeyError: 'default'

utdawn

inclusionAI org Feb 11

We recommend using transformers==4.57.1 for inference.

utdawn changed discussion status to closed Feb 11

cloudyu

Feb 11

for transformers-5.1.0 how to run it?
it's not reasonable to use transformers==4.57.1 only.

utdawn

inclusionAI org Feb 11

Thank you for bringing this to our attention.

The error occurs because the default strategy was removed from ROPE_INIT_FUNCTIONS[self.rope_type] in transformers 5.1.0. We are aware of this breaking change and will update our modeling files shortly to ensure compatibility with the latest version.

utdawn changed discussion status to open Feb 11

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