Downloads · 30 days
6
1% of all-time downloads
metacognitive-behavioral-tuning
Qwen3-4B-MBT-R
metacognitive-behavioral-tuning/Qwen3-4B-MBT-R
Qwen3-4B-MBT-R is a text generation model from metacognitive-behavioral-tuning. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
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.
All-time downloads
440
Public
Parameters
4.4B
8.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.8 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Jul 3, 2026
- Updated
- Jul 3, 2026
- SHA
- 506a7c7d
Try a prompt
Base models
Model card
From the Hugging Face model README
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")
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Languages
- en
- Created
- Jul 3, 2026
- Updated
- Jul 3, 2026