Instructions to use BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final with Transformers:

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

pipe = pipeline("text-generation", model="BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final")
model = AutoModelForCausalLM.from_pretrained("BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final

SGLang

How to use BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final 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 "BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final" \
    --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": "BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final",
		"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 "BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final" \
        --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": "BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final with Docker Model Runner:
```
docker model run hf.co/BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final
```

Open-MOPD-SmolLM3-3B-Final

This is the final flagship model from the Open-MOPD pipeline. Starting from BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-MixSFT, it is trained with multi-teacher online policy distillation using three domain-specific RL teachers for math, code, and instruction following. This release corresponds to training step 200.

Each prompt is hard-routed to its domain teacher. The dense reward is the teacher-student log-probability gap over the student's top-k distribution (k=16, nucleus p=0.99), weighted by the student probabilities and applied directly as the token-level advantage.

Open-MOPD uses three mechanisms to prevent cross-domain training imbalance:

Token-share balancing keeps the weighted gradient-token share near one third per domain. Without it, math and code consume about 99% of gradient tokens.
Gap-aware allocation (alpha=1) shifts the training budget toward domains with more remaining teacher-student improvement.
Reward refresh recomputes the student-dependent part of the dense reward at every inner update without adding extra prefills.

Training uses a global batch size of 1,024, mini-batch size 256, constant learning rate 1.5e-6, clipping at 0.2/0.28, no KL penalty, and a domain sampling ratio of math:code:IF = 2:2:1.

Results

Method	Math	Code	IF	Overall	Recovery
RouteRL teacher upper bound	24.24	21.73	51.08	32.35	100%
Open-MOPD Final	22.42	21.73	49.58	31.24	83.4%
Naive multi-teacher OPD	21.26	19.26	43.64	28.05	35.6%
MixSFT starting point	17.95	17.60	41.46	25.67	-

Per-dataset scores are AIME24 21.98, AIME25 22.86, LiveCodeBench v5 20.84, LiveCodeBench v6 22.63, IFEval 74.49, and IFBench_test 24.67. Recovery measures the fraction of the overall score gap between MixSFT and the routed-teacher upper bound recovered by the final student.

Evaluation protocol

Results are averaged per dataset, then per domain, followed by a macro-average over the three domains.

Math: AIME24 and AIME25, avg@64, temperature 0.6.
Code: LiveCodeBench v5 and v6, avg@10, temperature 1.0.
Instruction following: IFEval and IFBench_test, n=1, temperature 1.0, with enable_thinking=true.

All evaluations use max_model_len=32768, top_p=0.95, top_k=-1, and stop_token_ids=[128012]. Code is reported as avg@10, not best@10.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "BytedTsinghua-SIA/Open-MOPD-SmolLM3-3B-Final"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    dtype="bfloat16",
    device_map="auto",
)

messages = [{"role": "user", "content": "Find all real solutions of x^3 - 3x + 1 = 0."}]
inputs = tokenizer.apply_chat_template(
    messages,
    return_tensors="pt",
    add_generation_prompt=True,
    enable_thinking=True,
).to(model.device)

outputs = model.generate(
    inputs,
    max_new_tokens=8192,
    temperature=0.6,
    top_p=0.95,
    do_sample=True,
)
print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))