Instructions to use chris0809/tinyLLM-0.51B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chris0809/tinyLLM-0.51B-SFT with Transformers:

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

pipe = pipeline("text-generation", model="chris0809/tinyLLM-0.51B-SFT", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("chris0809/tinyLLM-0.51B-SFT", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use chris0809/tinyLLM-0.51B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chris0809/tinyLLM-0.51B-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chris0809/tinyLLM-0.51B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/chris0809/tinyLLM-0.51B-SFT

SGLang

How to use chris0809/tinyLLM-0.51B-SFT 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 "chris0809/tinyLLM-0.51B-SFT" \
    --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": "chris0809/tinyLLM-0.51B-SFT",
		"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 "chris0809/tinyLLM-0.51B-SFT" \
        --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": "chris0809/tinyLLM-0.51B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use chris0809/tinyLLM-0.51B-SFT with Docker Model Runner:
```
docker model run hf.co/chris0809/tinyLLM-0.51B-SFT
```

tinyLLM SFT 0.51B

中文项目文档 · English project overview · Live demo

One SFT base: mathematical reasoning with a verified answer, then tested Python code.

tinyLLM is a custom 0.51B decoder-only model trained from scratch for Chinese and English. Loading requires trust_remote_code=True because the architecture is implemented in this repository.

The released SFT checkpoint scores 50.64% (668/1319) on GSM8K with the project's greedy evaluation setup. It is also the shared base for the ARC GRPO, IFEval OPD and VLM releases.

Load

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "chris0809/tinyLLM-0.51B-SFT"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    trust_remote_code=True,
    dtype="auto",
)

Thinking mode

Ordinary chat uses the default template. For mathematics or multi-step reasoning, turn on the bundled switch; the template automatically injects the same reasoning protocol used during training and evaluation.

messages = [{"role": "user", "content": "Solve: 17 * 6. Give the final answer clearly."}]
inputs = tokenizer.apply_chat_template(
    messages,
    enable_thinking=True,
    add_generation_prompt=True,
    return_tensors="pt",
)

Omit enable_thinking or set it to False for ordinary chat. The thought boundaries are encoded with existing tokenizer pieces, so do not add special tokens or resize the embeddings. For GSM8K/ARC-style evaluation, append Put your final answer in LaTeX boxed form like $\boxed{answer}$. to the user question.

Task LoRAs can be attached without reloading the base model:

model.load_lora_pretrained("chris0809/tinyLLM-0.51B-ARC-GRPO")

Try the SFT checkpoint in the hosted tinyLLM demo. The Space uses free ZeroGPU, so a cold start or queue is normal.

Source

Training code and full project documentation: https://github.com/Huanz86251/tinyLLM

Downloads last month: 668

Safetensors

Model size

0.5B params

Tensor type

F32

Model tree for chris0809/tinyLLM-0.51B-SFT

Adapters

2 models

Finetunes

1 model

chris0809
/

tinyLLM-0.51B-SFT

tinyLLM SFT 0.51B

Load

Thinking mode

Source

Model tree for chris0809/tinyLLM-0.51B-SFT

Space using chris0809/tinyLLM-0.51B-SFT 1