Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+tags:
+- diffusion
+- flow-matching
+- rectified-flow
+- text-generation
+- reasoning
+- qwen2.5
+- block-diffusion
+pipeline_tag: text-generation
+language:
+- en
+---
+
+# BlockDiffuse: Parallel Multi-Block Reasoning Generation in Latent Space
+
+**BlockDiffuse** is a non-autoregressive / block-autoregressive diffusion framework that generates entire blocks of 100 tokens simultaneously in continuous latent space using Rectified Flow Matching.
+
+By coupling a Diffusion Transformer (DiT) with a frozen decoder-only Base LLM (`Qwen/Qwen2.5-0.5B-Instruct`), BlockDiffuse bypasses token-by-token sequential decoding, achieving parallel multi-token throughput.
+
+## Model Summary
+
+- **Base LLM**: `Qwen/Qwen2.5-0.5B-Instruct`
+- **DiT Architecture**: 8 Transformer Blocks with 14 Attention Heads ($d_\text{model}=896$, head dim 64)
+- **Latent Space**: Mid-layer representations (layer 12) for prompt conditioning; target 100-token blocks supervised via Flow Matching.
+- **Initialization**: Transfer learning from layers 6–11 of Qwen2.5-0.5B.
+- **Projection Head**: Deep 3-layer MLP residual adapter before RMSNorm and discrete token decoding.
+- **Training Objectives**: Flow Matching Velocity MSE ($\mathcal{L}_\text{FM}$) + Dispersive Loss + Teacher KL Distillation + Discrete Token Cross-Entropy ($\mathcal{L}_\text{CE}$) + Contrastive InfoNCE Nearest-Neighbor Loss ($\mathcal{L}_\text{NN}$).
+
+## Benchmark Results on RTX 4070 Laptop GPU
+
+| Mode | Tokens | Diffusion Steps | Latency | Throughput |
+| :--- | :--- | :--- | :--- | :--- |
+| **Single-Block Parallel** | 100 tokens | 8 ODE steps (DPM-Solver + TFE) | **1,730.60 ms** | **57.78 tokens/sec** |
+| **Multi-Block Autoregressive** | 200 tokens (2 blocks) | 8 ODE steps per block | **1,279.20 ms** | **156.35 tokens/sec** |
+
+## Quickstart & Inference
+
+To run inference using the official repository [Hooshaai/BlockDiffuse](https://github.com/Hooshaai/BlockDiffuse):
+
+```bash
+git clone https://github.com/Hooshaai/BlockDiffuse.git
+cd BlockDiffuse
+
+python inference.py \
+    --model Qwen/Qwen2.5-0.5B-Instruct \
+    --checkpoint ./blockdiffuse_final.pt \
+    --prompt "<|im_start|>system\nYou are a helpful assistant that solves problems step by step.<|im_end|>\n<|im_start|>user\nA bookstore has 140 books on Monday. On Tuesday, they sell 45 books. On Wednesday, they receive 80 books. How many remain?<|im_end|>\n<|im_start|>assistant\n" \
+    --steps 8 \
+    --solver dpm_solver \
+    --use_tfe \
+    --tfe_seeds 3
+```
+
+## Citation
+
+```bibtex
+@software{blockdiffuse2026,
+  author = {Hooshaai Research},
+  title = {BlockDiffuse: Fully Parallel Latent Space Reasoning Generation with Diffusion Transformers},
+  year = {2026},
+  url = {https://github.com/Hooshaai/BlockDiffuse}
+}
+```