Instructions to use ssslakter/LLaDA-8B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ssslakter/LLaDA-8B-Base with Transformers:

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

pipe = pipeline("text-generation", model="ssslakter/LLaDA-8B-Base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ssslakter/LLaDA-8B-Base", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ssslakter/LLaDA-8B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ssslakter/LLaDA-8B-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": "ssslakter/LLaDA-8B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ssslakter/LLaDA-8B-Base

SGLang

How to use ssslakter/LLaDA-8B-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 "ssslakter/LLaDA-8B-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": "ssslakter/LLaDA-8B-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 "ssslakter/LLaDA-8B-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": "ssslakter/LLaDA-8B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ssslakter/LLaDA-8B-Base with Docker Model Runner:
```
docker model run hf.co/ssslakter/LLaDA-8B-Base
```

Slava Chaunin commited on 26 days ago

Commit

0d435a2

1 Parent(s): 478b3a3

fix model

Browse files

Files changed (2) hide show

configuration_llada.py +0 -2
modeling_llada.py +2 -4

configuration_llada.py CHANGED Viewed

@@ -444,8 +444,6 @@ class LLaDAConfig(PretrainedConfig):
         all_kwargs["use_cache"] = use_cache
         all_kwargs["architectures"] = all_kwargs.get("architectures", ["LLaDAModelLM"])
-        for key, value in kwargs.items():
-            setattr(self, key, value)
         super().__post_init__(**all_kwargs)
     @property

         all_kwargs["use_cache"] = use_cache
         all_kwargs["architectures"] = all_kwargs.get("architectures", ["LLaDAModelLM"])
         super().__post_init__(**all_kwargs)
     @property

modeling_llada.py CHANGED Viewed

@@ -1417,13 +1417,11 @@ class LLaDAModelLM(PreTrainedModel):
         attention_bias: Optional[torch.Tensor] = None,
         past_key_values: Optional[List[torch.FloatTensor]] = None,
         labels: Optional[torch.LongTensor] = None,
-        use_cache: Optional[bool] = None,
         output_attentions: Optional[bool] = None,
         output_hidden_states: Optional[bool] = None,
         **kwargs
     ) -> Union[Tuple, CausalLMOutputWithPast]:
-        if use_cache is None:
-            use_cache = self.config.use_cache
         if output_attentions:
             raise ValueError("output_attentions is not yet supported in LLaDA")
@@ -1465,7 +1463,7 @@ class LLaDAModelLM(PreTrainedModel):
         model_inputs = {"input_ids": input_ids, "past_key_values": past_key_values}
         model_inputs.update(kwargs)
-        model_inputs["use_cache"] = kwargs.pop("use_cache", self.config.use_cache)
         return model_inputs
     # TODO: these are required to make the implementation complete.

         attention_bias: Optional[torch.Tensor] = None,
         past_key_values: Optional[List[torch.FloatTensor]] = None,
         labels: Optional[torch.LongTensor] = None,
+        use_cache: Optional[bool] = False,
         output_attentions: Optional[bool] = None,
         output_hidden_states: Optional[bool] = None,
         **kwargs
     ) -> Union[Tuple, CausalLMOutputWithPast]:
         if output_attentions:
             raise ValueError("output_attentions is not yet supported in LLaDA")
         model_inputs = {"input_ids": input_ids, "past_key_values": past_key_values}
         model_inputs.update(kwargs)
+        model_inputs["use_cache"] = kwargs.pop("use_cache", False)
         return model_inputs
     # TODO: these are required to make the implementation complete.