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

Libraries

How to use Fraser/LLaDA-8B-Recursive-ARC with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Fraser/LLaDA-8B-Recursive-ARC", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Fraser/LLaDA-8B-Recursive-ARC with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Fraser/LLaDA-8B-Recursive-ARC"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Fraser/LLaDA-8B-Recursive-ARC",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Fraser/LLaDA-8B-Recursive-ARC

SGLang

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

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

LLaDA-8B-Recursive-ARC / tokenizer_config.json

Fraser

Upload folder using huggingface_hub

56be64d verified 3 months ago

raw

history blame contribute delete

2.56 kB

	{
	"add_bos_token": false,
	"add_eos_token": false,
	"added_tokens_decoder": {
	"75": {
	"content": "<\|startoftext\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"76": {
	"content": "<\|endoftext\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"77": {
	"content": "[CLS]",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"78": {
	"content": "<\|mdm_mask\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"79": {
	"content": "<role>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"80": {
	"content": "</role>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"81": {
	"content": "<\|arithmetic_start\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"82": {
	"content": "<\|arithmetic_end\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"83": {
	"content": "<\|number_start\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"84": {
	"content": "<\|number_end\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"additional_special_tokens": [
	"<\|mdm_mask\|>",
	"<role>",
	"</role>",
	"<\|arithmetic_start\|>",
	"<\|arithmetic_end\|>",
	"<\|number_start\|>",
	"<\|number_end\|>"
	],
	"bos_token": "<\|startoftext\|>",
	"clean_up_tokenization_spaces": false,
	"cls_token": "[CLS]",
	"eos_token": "<\|endoftext\|>",
	"extra_special_tokens": {},
	"fast_tokenizer": true,
	"gmask_token": "[gMASK]",
	"mask_token": "<\|mdm_mask\|>",
	"merges_file": null,
	"model_input_names": [
	"input_ids",
	"attention_mask"
	],
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<\|endoftext\|>",
	"padding_side": "right",
	"tokenizer_class": "PreTrainedTokenizerFast",
	"trust_remote_code": true
	}