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 Settings

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
```

utdawn commited on Feb 9

Commit

276abc9

verified ·

1 Parent(s): a8af0fb

Update configuration_llada2_moe.py

Browse files

Files changed (1) hide show

configuration_llada2_moe.py +5 -2

configuration_llada2_moe.py CHANGED Viewed

@@ -16,7 +16,7 @@ class LLaDA2MoeConfig(PretrainedConfig):
         num_key_value_heads=0,
         hidden_act="silu",
         use_qkv_bias=False,  # llada2 only
-        use_qk_norm=False,
         use_bias=True,  # llada2 only
         rms_norm_eps=1e-05,
         norm_head=False,  # llada2 only
@@ -54,6 +54,7 @@ class LLaDA2MoeConfig(PretrainedConfig):
         self.num_key_value_heads = num_key_value_heads
         self.hidden_act = hidden_act
         self.use_qkv_bias = use_qkv_bias
         self.use_bias = use_bias
         self.norm_head = norm_head
         self.rms_norm_eps = rms_norm_eps
@@ -82,4 +83,6 @@ class LLaDA2MoeConfig(PretrainedConfig):
         self.routed_scaling_factor = routed_scaling_factor
         self.partial_rotary_factor = partial_rotary_factor
-        super().__init__(pad_token_id=pad_token_id, tie_word_embeddings=tie_word_embeddings, **kwargs)

         num_key_value_heads=0,
         hidden_act="silu",
         use_qkv_bias=False,  # llada2 only
+        use_qk_norm=True,
         use_bias=True,  # llada2 only
         rms_norm_eps=1e-05,
         norm_head=False,  # llada2 only
         self.num_key_value_heads = num_key_value_heads
         self.hidden_act = hidden_act
         self.use_qkv_bias = use_qkv_bias
+        self.use_qk_norm = use_qk_norm
         self.use_bias = use_bias
         self.norm_head = norm_head
         self.rms_norm_eps = rms_norm_eps
         self.routed_scaling_factor = routed_scaling_factor
         self.partial_rotary_factor = partial_rotary_factor
+        super().__init__(
+            pad_token_id=pad_token_id, tie_word_embeddings=tie_word_embeddings, **kwargs
+        )