Instructions to use metacognitive-behavioral-tuning/Qwen3-4B-MBT-R with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use metacognitive-behavioral-tuning/Qwen3-4B-MBT-R with Transformers:

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

pipe = pipeline("text-generation", model="metacognitive-behavioral-tuning/Qwen3-4B-MBT-R")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("metacognitive-behavioral-tuning/Qwen3-4B-MBT-R")
model = AutoModelForCausalLM.from_pretrained("metacognitive-behavioral-tuning/Qwen3-4B-MBT-R")
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 metacognitive-behavioral-tuning/Qwen3-4B-MBT-R with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/metacognitive-behavioral-tuning/Qwen3-4B-MBT-R

SGLang

How to use metacognitive-behavioral-tuning/Qwen3-4B-MBT-R 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 "metacognitive-behavioral-tuning/Qwen3-4B-MBT-R" \
    --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": "metacognitive-behavioral-tuning/Qwen3-4B-MBT-R",
		"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 "metacognitive-behavioral-tuning/Qwen3-4B-MBT-R" \
        --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": "metacognitive-behavioral-tuning/Qwen3-4B-MBT-R",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use metacognitive-behavioral-tuning/Qwen3-4B-MBT-R with Docker Model Runner:
```
docker model run hf.co/metacognitive-behavioral-tuning/Qwen3-4B-MBT-R
```

Qwen3-4B · MBT-R

MBT-R (main table) — final checkpoint (SFT → GRPO). Base: Qwen/Qwen3-4B. Paper: Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering.

Method: MBT-R (Refinement): the student's own reasoning traces are rewritten into the 5-phase structure for SFT, then GRPO.
Base model: Qwen/Qwen3-4B
Training: SFT (LR 1e-4, BS 128, HotpotQA) → GRPO
Benchmarks: HotpotQA (ID), MuSiQue / 2WikiMultiHopQA (OOD)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "metacognitive-behavioral-tuning/Qwen3-4B-MBT-R"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, dtype="bfloat16", device_map="auto")

Downloads last month: 319

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for metacognitive-behavioral-tuning/Qwen3-4B-MBT-R

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

(863)

this model