Given a question and its answer, the model learns to produce the step-by-step reasoning chain that bridges the question to the answer. This trains the model to generate coherent chain-of-thought reasoning via DREAM's masked diffusion process.

Input: Question + Answer
Output: Detailed reasoning trace connecting them

Training Details

Base model: Dream-org/Dream-v0-Instruct-7B
Training data: 75,000 examples from KIMI-K2.5-1000000x (General-Distillation subset)
Objective: DREAM masked diffusion with CART time reweighting
Hardware: 8x NVIDIA H100 80GB
Epochs: 3
Batch size: 128
Learning rate: 2e-6 (cosine schedule)
Max sequence length: 2048 tokens
Precision: bf16 mixed precision (FSDP)

Usage

python

from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("WilhelmH/Bridge-7b-Diffusion", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("WilhelmH/Bridge-7b-Diffusion", trust_remote_code=True)

Architecture

This is a masked diffusion language model (not autoregressive). It uses bidirectional attention and generates text by iteratively denoising masked tokens. See the DREAM paper for details.

WilhelmH/Bridge-7b-Diffusion-Full

Bridge-7b-Diffusion

What is ReverseThought?

Training Details

Usage

Architecture

WilhelmH/
Bridge-7b-Diffusion-Full