Instructions to use inclusionAI/LLaDA2.0-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inclusionAI/LLaDA2.0-mini with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/LLaDA2.0-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/LLaDA2.0-mini", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use inclusionAI/LLaDA2.0-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inclusionAI/LLaDA2.0-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/LLaDA2.0-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inclusionAI/LLaDA2.0-mini

SGLang

How to use inclusionAI/LLaDA2.0-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/LLaDA2.0-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/LLaDA2.0-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/LLaDA2.0-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/LLaDA2.0-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inclusionAI/LLaDA2.0-mini with Docker Model Runner:
```
docker model run hf.co/inclusionAI/LLaDA2.0-mini
```

fix: exclude prompt tokens in generate() return value

by haahha - opened Nov 28, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-1

Files changed (1) hide show

modeling_llada2_moe.py +1 -1

modeling_llada2_moe.py CHANGED Viewed

@@ -1409,7 +1409,7 @@ class LLaDA2MoeModelLM(LLaDA2MoePreTrainedModel, GenerationMixin):
                     if len(eos_pos_in_x[0]) > 0:
                         eos_pos = eos_pos_in_x[0][0].item()
                         if (cur_x[0, prompt_length:eos_pos] != mask_id).all():
-                            final_x = x[:, :total_length][:, : eos_pos + 1]
                             return final_x
             x[:, :current_window_end] = cur_x

                     if len(eos_pos_in_x[0]) > 0:
                         eos_pos = eos_pos_in_x[0][0].item()
                         if (cur_x[0, prompt_length:eos_pos] != mask_id).all():
+                            final_x = x[:, :total_length][:, prompt_length : eos_pos + 1]
                             return final_x
             x[:, :current_window_end] = cur_x