Instructions to use LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint with Transformers:

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

pipe = pipeline("text-generation", model="LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint")
model = AutoModelForCausalLM.from_pretrained("LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint

SGLang

How to use LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint 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 "LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint" \
    --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": "LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint",
		"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 "LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint" \
        --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": "LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint with Docker Model Runner:
```
docker model run hf.co/LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint
```

SPSD-RL Qwen3-4B Instruct 2507 SDFT MCTSStyle ConciseHint

This is the final loadable model root from the 400-step SDFT run qwen3-4b-instruct-2507-sdft-mctsstyle-parity400-concisehint-lr1em6-cumem0-20260615. It starts from Qwen/Qwen3-4B-Instruct-2507 and trains on LorMolf/SPSD-RL using TRL experimental self-distillation with MCTS-style privileged contexts.

Training Summary

Method: SDFT over prompt plus privileged MCTS-context rows.
Budget: 400 optimizer steps with generation_batch_size=128, or 51,200 generated completions.
Learning rate: 1e-6.
Runtime: four H200 GPUs, DDP, NCCL_CUMEM_ENABLE=0, USE_FSDP=false.
Student concise hint: enabled.
generate_from_teacher: false.
Train-time eval: disabled (eval_strategy=no) because the TRL SDFT eval path is incompatible with raw prompt/privileged-context batches in this setup.
W&B run: x2tz41er in project olmo-spiral-sdft.

The final trainer summary recorded train loss 0.05229, runtime about 1.133e+05 seconds, train samples/s 0.452, and train steps/s 0.004.

Artifact Scope

This Hugging Face repository intentionally contains only the final loadable model payload: model weights, tokenizer/config files, generation config, chat template, and this model card. Intermediate checkpoint-* directories, optimizer/scheduler state, trainer state, logs, caches, and dataset materialization artifacts are not included.

Evaluation

Post-hoc reasoning and OpenReward/CRPT game evaluations should use the repository standard boxed SFT/SDFT profile (sft_boxed_forced) so visible reasoning is preserved while final answers are canonicalized to Final answer: \boxed{...} when needed. No post-hoc benchmark results are included in this model card at upload time.

Downloads last month: 13

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(2726)

this model

LorMolf
/

SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint

SPSD-RL Qwen3-4B Instruct 2507 SDFT MCTSStyle ConciseHint

Training Summary

Artifact Scope

Evaluation

Model tree for LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint

Dataset used to train LorMolf/SPSD-RL-Qwen3-4B-Instruct-2507-SDFT-MCTSStyle-ConciseHint