Instructions to use Tiiny/SmallThinker-4BA0.6B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tiiny/SmallThinker-4BA0.6B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Tiiny/SmallThinker-4BA0.6B-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Tiiny/SmallThinker-4BA0.6B-Instruct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Tiiny/SmallThinker-4BA0.6B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tiiny/SmallThinker-4BA0.6B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tiiny/SmallThinker-4BA0.6B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Tiiny/SmallThinker-4BA0.6B-Instruct

SGLang

How to use Tiiny/SmallThinker-4BA0.6B-Instruct 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 "Tiiny/SmallThinker-4BA0.6B-Instruct" \
    --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": "Tiiny/SmallThinker-4BA0.6B-Instruct",
		"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 "Tiiny/SmallThinker-4BA0.6B-Instruct" \
        --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": "Tiiny/SmallThinker-4BA0.6B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Tiiny/SmallThinker-4BA0.6B-Instruct with Docker Model Runner:
```
docker model run hf.co/Tiiny/SmallThinker-4BA0.6B-Instruct
```

SmallThinker-4BA0.6B-Instruct / config.json

Yixin Song

Upload folder using huggingface_hub

84b3156 verified about 1 year ago

Raw

History Blame Contribute Delete

1.69 kB

	{
	"architectures": [
	"SmallThinkerForCausalLM"
	],
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_smallthinker.SmallThinkerConfig",
	"AutoModel": "modeling_smallthinker.SmallThinkerForCausalLM",
	"AutoModelForCausalLM": "modeling_smallthinker.SmallThinkerForCausalLM"
	},
	"bos_token_id": 151643,
	"eos_token_id": [151643,151645],
	"head_dim": 128,
	"hidden_size": 1536,
	"initializer_range": 0.02,
	"max_length": null,
	"max_position_embeddings": 32768,
	"model_name": "smallthinker_4b_instruct",
	"model_type": "smallthinker",
	"moe_ffn_hidden_size": 768,
	"moe_num_active_primary_experts": 4,
	"moe_num_primary_experts": 32,
	"norm_topk_prob": true,
	"num_attention_heads": 12,
	"num_hidden_layers": 32,
	"num_key_value_heads": 2,
	"output_router_logits": false,
	"repetition_penalty": null,
	"rms_norm_eps": 1e-06,
	"rope_layout": [
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1
	],
	"rope_scaling": null,
	"rope_theta": 1.5e6,
	"sliding_window_size": 4096,
	"sliding_window_layout": [
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0
	],
	"temperature": null,
	"tie_word_embeddings": true,
	"tokenizer_class": "Qwen2Tokenizer",
	"top_p": null,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.53.3",
	"use_cache": false,
	"vocab_size": 151936
	}