Feature Extraction
Transformers
PyTorch
Chinese
English
recommendation
dual-tower
transformer
multi-hash-embedding
Instructions to use DreamMachine-AI/Dream-Machine with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DreamMachine-AI/Dream-Machine with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="DreamMachine-AI/Dream-Machine")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("DreamMachine-AI/Dream-Machine", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Init redirect model card for DreamMachine-AI/Dream-Machine
Browse files
README.md
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
language:
|
| 4 |
+
- zh
|
| 5 |
+
- en
|
| 6 |
+
tags:
|
| 7 |
+
- recommendation
|
| 8 |
+
- dual-tower
|
| 9 |
+
- transformer
|
| 10 |
+
- multi-hash-embedding
|
| 11 |
+
- pytorch
|
| 12 |
+
library_name: transformers
|
| 13 |
+
pipeline_tag: feature-extraction
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<div style="max-width:100%;overflow:hidden;">
|
| 17 |
+
<pre style="
|
| 18 |
+
background:#0d0d0d;
|
| 19 |
+
font-family:'Courier New',Courier,monospace;
|
| 20 |
+
font-size:clamp(3.5px,0.82vw,10px);
|
| 21 |
+
line-height:1.15;
|
| 22 |
+
padding:0.9em 1.1em;
|
| 23 |
+
border-radius:12px;
|
| 24 |
+
white-space:pre;
|
| 25 |
+
overflow:hidden;
|
| 26 |
+
max-width:100%;
|
| 27 |
+
box-sizing:border-box;
|
| 28 |
+
color:transparent;
|
| 29 |
+
background-clip:text;
|
| 30 |
+
-webkit-background-clip:text;
|
| 31 |
+
background-image:linear-gradient(
|
| 32 |
+
118deg,
|
| 33 |
+
#FF6B6B 0%,
|
| 34 |
+
#FF8C42 20%,
|
| 35 |
+
#FFCF48 40%,
|
| 36 |
+
#FFFFFF 55%,
|
| 37 |
+
#FFCF48 70%,
|
| 38 |
+
#FF8C42 85%,
|
| 39 |
+
#FF6B6B 100%
|
| 40 |
+
);
|
| 41 |
+
">βββββββ βββββββ ββββββββ ββββββ ββββ ββββββββ ββββ ββββββ ββββββββββ ββββββββββ βββββββββββ
|
| 42 |
+
βββββββββββββββββββββββββββββββββββββ ββββββββββ ββββββββββββββββββββββββ βββββββββββ βββββββββββ
|
| 43 |
+
βββ βββββββββββββββββ βββββββββββββββββββββββββββββββββββββββββ βββββββββββββββββ βββββββββ
|
| 44 |
+
βββ βββββββββββββββββ βββββββββββββββββββββββββββββββββββββββββ βββββββββββββββββββββββββββ
|
| 45 |
+
βββββββββββ ββββββββββββββ ββββββ βββ ββββββ βββ ββββββ ββββββββββββββ βββββββββ ββββββββββββββ
|
| 46 |
+
βββββββ βββ ββββββββββββββ ββββββ ββββββ ββββββ βββ ββββββββββ βββββββββ βββββββββββββ</pre>
|
| 47 |
+
</div>
|
| 48 |
+
|
| 49 |
+
<div align="center">
|
| 50 |
+
|
| 51 |
+
<p style="font-size:1.5em;font-weight:900;letter-spacing:0.03em;margin:0.2em 0 0.1em;">
|
| 52 |
+
β¨ Dream-Machine β Billion-Item Neural Recommendation Sorcerer β¨
|
| 53 |
+
</p>
|
| 54 |
+
|
| 55 |
+
<p style="font-size:1.0em;font-weight:500;color:#aaa;margin:0 0 1em;">
|
| 56 |
+
Multi-Hash Transformer Dual-Tower Β· RAG-Enhanced Β· Production-Grade Β· 10<sup>10</sup> Scale
|
| 57 |
+
</p>
|
| 58 |
+
|
| 59 |
+
[](https://huggingface.co/dream-machine-ai/Dream-Machine-08-09)
|
| 60 |
+
[](https://huggingface.co/datasets/dream-machine-ai/Dream-Machine-08-09-Dataset)
|
| 61 |
+
[](https://huggingface.co/spaces/dream-machine-ai/)
|
| 62 |
+
[](https://doi.org/10.5281/zenodo.21906715)
|
| 63 |
+
[](https://creativecommons.org/licenses/by-nc/4.0/)
|
| 64 |
+
|
| 65 |
+
</div>
|
| 66 |
+
|
| 67 |
+
---
|
| 68 |
+
|
| 69 |
+
## π Repository Notice
|
| 70 |
+
|
| 71 |
+
> **This repository is the official DreamMachine-AI organization listing.**
|
| 72 |
+
> The full model weights, code, and documentation are published under the
|
| 73 |
+
> **[dream-machine-ai](https://huggingface.co/dream-machine-ai)** account namespace.
|
| 74 |
+
|
| 75 |
+
| Resource | Location |
|
| 76 |
+
|:---------|:---------|
|
| 77 |
+
| π€ **Full Model Card + Weights** | [dream-machine-ai/Dream-Machine-08-09](https://huggingface.co/dream-machine-ai/Dream-Machine-08-09) |
|
| 78 |
+
| π¦ **Training Dataset** | [dream-machine-ai/Dream-Machine-08-09-Dataset](https://huggingface.co/datasets/dream-machine-ai/Dream-Machine-08-09-Dataset) |
|
| 79 |
+
| π **Interactive Space** | [spaces/dream-machine-ai](https://huggingface.co/spaces/dream-machine-ai/) |
|
| 80 |
+
| π’ **Organization Hub** | [DreamMachine-AI](https://huggingface.co/DreamMachine-AI) |
|
| 81 |
+
| π **Technical Report** | [Zenodo 10.5281/zenodo.21906715](https://doi.org/10.5281/zenodo.21906715) |
|
| 82 |
+
| π» **Source Code** | [GitHub / Dream-Machine](https://github.com/When-Summer-Understands-Winter/Dream-Machine/) |
|
| 83 |
+
|
| 84 |
+
---
|
| 85 |
+
|
| 86 |
+
## β‘ Quick Load
|
| 87 |
+
|
| 88 |
+
```python
|
| 89 |
+
from transformers import AutoConfig, AutoModel
|
| 90 |
+
|
| 91 |
+
model = AutoModel.from_pretrained(
|
| 92 |
+
"dream-machine-ai/Dream-Machine-08-09",
|
| 93 |
+
trust_remote_code=True,
|
| 94 |
+
).eval()
|
| 95 |
+
```
|
| 96 |
+
|
| 97 |
+
```python
|
| 98 |
+
from huggingface_hub import snapshot_download
|
| 99 |
+
|
| 100 |
+
# Full model repository
|
| 101 |
+
model_path = snapshot_download(repo_id="dream-machine-ai/Dream-Machine-08-09")
|
| 102 |
+
|
| 103 |
+
# Training dataset
|
| 104 |
+
dataset_path = snapshot_download(
|
| 105 |
+
repo_id="dream-machine-ai/Dream-Machine-08-09-Dataset",
|
| 106 |
+
repo_type="dataset",
|
| 107 |
+
)
|
| 108 |
+
```
|
| 109 |
+
|
| 110 |
+
---
|
| 111 |
+
|
| 112 |
+
## π Benchmarks
|
| 113 |
+
|
| 114 |
+
| Metric | Value |
|
| 115 |
+
|:-------|:-----:|
|
| 116 |
+
| **AUC** | **0.4849** |
|
| 117 |
+
| **HR@10** | **1.0** |
|
| 118 |
+
| **NDCG@10** | **0.537** |
|
| 119 |
+
| E2E Latency | **β€ 100 ms** |
|
| 120 |
+
| Max Catalogue | **10ΒΉβ° items** |
|
| 121 |
+
|
| 122 |
+
---
|
| 123 |
+
|
| 124 |
+
## βοΈ License
|
| 125 |
+
|
| 126 |
+
This project is licensed under the **Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0)**.
|
| 127 |
+
|
| 128 |
+
| β
Permitted | β Prohibited |
|
| 129 |
+
|:---|:---|
|
| 130 |
+
| Academic research & publication | Commercial products or services |
|
| 131 |
+
| Personal learning & experimentation | Revenue-generating deployments |
|
| 132 |
+
| Non-commercial derivative works | Sublicensing for profit |
|
| 133 |
+
| Citing in papers with attribution | Any business use without written permission |
|
| 134 |
+
|
| 135 |
+
> **Commercial use of any kind β including integrating model weights, code, or outputs into a product or service β requires explicit prior written consent from the author (Fangjun Wen).**
|
| 136 |
+
> Contact: fangjunwen168@outlook.com
|
| 137 |
+
|
| 138 |
+
[](https://creativecommons.org/licenses/by-nc/4.0/)
|
| 139 |
+
|
| 140 |
+
---
|
| 141 |
+
|
| 142 |
+
<div align="center">
|
| 143 |
+
|
| 144 |
+
**Paper**: [DreamMachine: A Billion-Item Neural Recommendation Sorcerer](https://doi.org/10.5281/zenodo.21906715)
|
| 145 |
+
**Author**: Fangjun Wen Β· DreamMachine Research Team Β· August 2026
|
| 146 |
+
|
| 147 |
+
`// built with focus Β· DreamMachine Research`
|
| 148 |
+
|
| 149 |
+
</div>
|