Instructions to use DuoNeural/SmolLM2-360M-Think-R18 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DuoNeural/SmolLM2-360M-Think-R18 with Transformers:

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

pipe = pipeline("text-generation", model="DuoNeural/SmolLM2-360M-Think-R18")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("DuoNeural/SmolLM2-360M-Think-R18")
model = AutoModelForMultimodalLM.from_pretrained("DuoNeural/SmolLM2-360M-Think-R18")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DuoNeural/SmolLM2-360M-Think-R18 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DuoNeural/SmolLM2-360M-Think-R18"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DuoNeural/SmolLM2-360M-Think-R18",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DuoNeural/SmolLM2-360M-Think-R18

SGLang

How to use DuoNeural/SmolLM2-360M-Think-R18 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 "DuoNeural/SmolLM2-360M-Think-R18" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DuoNeural/SmolLM2-360M-Think-R18",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "DuoNeural/SmolLM2-360M-Think-R18" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DuoNeural/SmolLM2-360M-Think-R18",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DuoNeural/SmolLM2-360M-Think-R18 with Docker Model Runner:
```
docker model run hf.co/DuoNeural/SmolLM2-360M-Think-R18
```

SmolLM2-360M-Think-R18 / tokenizer_config.json

DuoNeural

DuoNeural Think Instillation R18 — dead-prompt filtered GRPO, +0.030 over post-SFT

e86cf4d verified 4 days ago

Raw

History Blame Contribute Delete

881 Bytes

	{
	"add_prefix_space": false,
	"backend": "tokenizers",
	"bos_token": "<\|endoftext\|>",
	"clean_up_tokenization_spaces": false,
	"eos_token": "<\|endoftext\|>",
	"errors": "replace",
	"extra_special_tokens": [
	"<\|endoftext\|>",
	"<\|im_start\|>",
	"<\|im_end\|>",
	"<repo_name>",
	"<reponame>",
	"<file_sep>",
	"<filename>",
	"<gh_stars>",
	"<issue_start>",
	"<issue_comment>",
	"<issue_closed>",
	"<jupyter_start>",
	"<jupyter_text>",
	"<jupyter_code>",
	"<jupyter_output>",
	"<jupyter_script>",
	"<empty_output>"
	],
	"is_local": true,
	"local_files_only": false,
	"max_length": 384,
	"model_max_length": 8192,
	"pad_token": "<\|im_start\|>",
	"stride": 0,
	"tokenizer_class": "GPT2Tokenizer",
	"truncation_side": "right",
	"truncation_strategy": "longest_first",
	"unk_token": "<\|endoftext\|>",
	"vocab_size": 49152
	}