Instructions to use apple/SimpleSD-4B-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use apple/SimpleSD-4B-instruct with Transformers:

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

pipe = pipeline("text-generation", model="apple/SimpleSD-4B-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("apple/SimpleSD-4B-instruct")
model = AutoModelForCausalLM.from_pretrained("apple/SimpleSD-4B-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use apple/SimpleSD-4B-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "apple/SimpleSD-4B-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": "apple/SimpleSD-4B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/apple/SimpleSD-4B-instruct

SGLang

How to use apple/SimpleSD-4B-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 "apple/SimpleSD-4B-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": "apple/SimpleSD-4B-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 "apple/SimpleSD-4B-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": "apple/SimpleSD-4B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use apple/SimpleSD-4B-instruct with Docker Model Runner:
```
docker model run hf.co/apple/SimpleSD-4B-instruct
```

yizheapple commited on Apr 6

Commit

7f2f78c

verified ·

1 Parent(s): b05f230

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -10,7 +10,7 @@ library_name: transformers
 # SimpleSD-4B-instruct
-This model was produced using **Simple Self-Distillation (SSD)**, a method that improves code generation by fine-tuning a language model on its own sampled outputs—without rewards, verifiers, teacher models, or reinforcement learning.
 - **Self-distillation sampling:** temperature=1.6, top_p=0.8, top_k=20
 - **Evaluation sampling:** temperature=1.1, top_p=0.8, top_k=20
@@ -31,7 +31,7 @@ tokenizer = AutoTokenizer.from_pretrained("apple/SimpleSD-4B-instruct")
 ## Method
-SSD samples solutions from the base model using non-unit temperature and top-k/top-p truncation, then fine-tunes on those samples via standard supervised learning. Despite its simplicity, SSD yields large gains on competitive programming benchmarks, with improvements concentrating on harder problems. The mechanism traces to resolving a *precision–exploration conflict*: SSD reshapes token distributions in a context-dependent way so that a single global decoding configuration becomes far more effective at evaluation time.
 ## Results
@@ -40,7 +40,7 @@ LiveCodeBench (%)
 | Model | LCBv6 pass@1 | LCBv6 pass@5 | LCBv5 pass@1 | LCBv5 pass@5 |
 |---|---|---|---|---|
 | Qwen3-4B-Instruct-2507 (base) | 34.0 | 41.0 | 34.3 | 45.4 |
-| **+ SSD (this model)** | **41.5** (+7.5) | **56.8** (+15.8) | **45.7** (+11.4) | **61.9** (+16.5) |
 ## Paper

 # SimpleSD-4B-instruct
+This model was produced using **Simple Self-Distillation (SimpleSD)**, a method that improves code generation by fine-tuning a language model on its own sampled outputs—without rewards, verifiers, teacher models, or reinforcement learning.
 - **Self-distillation sampling:** temperature=1.6, top_p=0.8, top_k=20
 - **Evaluation sampling:** temperature=1.1, top_p=0.8, top_k=20
 ## Method
+SimpleSD samples solutions from the base model using non-unit temperature and top-k/top-p truncation, then fine-tunes on those samples via standard supervised learning. Despite its simplicity, SimpleSD yields large gains on competitive programming benchmarks, with improvements concentrating on harder problems. The mechanism traces to resolving a *precision–exploration conflict*: SimpleSD reshapes token distributions in a context-dependent way so that a single global decoding configuration becomes far more effective at evaluation time.
 ## Results
 | Model | LCBv6 pass@1 | LCBv6 pass@5 | LCBv5 pass@1 | LCBv5 pass@5 |
 |---|---|---|---|---|
 | Qwen3-4B-Instruct-2507 (base) | 34.0 | 41.0 | 34.3 | 45.4 |
+| **+ SimpleSD (this model)** | **41.5** (+7.5) | **56.8** (+15.8) | **45.7** (+11.4) | **61.9** (+16.5) |
 ## Paper