Feature Extraction
Transformers
PyTorch
English
minicpmv
information retrieval
embedding model
visual information retrieval
custom_code
Instructions to use RhapsodyAI/MiniCPM-V-Embedding-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RhapsodyAI/MiniCPM-V-Embedding-preview with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="RhapsodyAI/MiniCPM-V-Embedding-preview", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("RhapsodyAI/MiniCPM-V-Embedding-preview", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -31,7 +31,7 @@ Our model is capable of:
|
|
| 31 |
|
| 32 |
- 2024-08-17: ๐ We open-sourced [cleaned version of training codebase](https://github.com/RhapsodyAILab/MiniCPM-V-Embedding-v0-Train) for MiniCPM-Visual-Embedding, which supports **deepspeed zero stage 1,2** and **large batchsize** like `4096` for full-parameter training to turn VLMs into dense retrievers. We also developed methods to filter training datasets and generating queries using unlablled datasets. We supports **multi-nodes, multi-GPUs** high-efficiency **evaluation** on large retrieval datasets. With such efforts, we support up to `20B` VLM contrastive learning with `4096` batch size. We have tested that one can train a VLM dense retriever with only **1 GPU, but with batch size of `4096`**.
|
| 33 |
|
| 34 |
-
- 2024-07-14: ๐ค We released **online huggingface demo**! Try our [online demo](https://huggingface.co/spaces/bokesyo/
|
| 35 |
|
| 36 |
- 2024-07-14: ๐ We released a **locally deployable Gradio demo** of `Memex`, take a look at [pipeline_gradio.py](https://huggingface.co/RhapsodyAI/minicpm-visual-embedding-v0/blob/main/pipeline_gradio.py). You can build a demo on your PC now!
|
| 37 |
|
|
|
|
| 31 |
|
| 32 |
- 2024-08-17: ๐ We open-sourced [cleaned version of training codebase](https://github.com/RhapsodyAILab/MiniCPM-V-Embedding-v0-Train) for MiniCPM-Visual-Embedding, which supports **deepspeed zero stage 1,2** and **large batchsize** like `4096` for full-parameter training to turn VLMs into dense retrievers. We also developed methods to filter training datasets and generating queries using unlablled datasets. We supports **multi-nodes, multi-GPUs** high-efficiency **evaluation** on large retrieval datasets. With such efforts, we support up to `20B` VLM contrastive learning with `4096` batch size. We have tested that one can train a VLM dense retriever with only **1 GPU, but with batch size of `4096`**.
|
| 33 |
|
| 34 |
+
- 2024-07-14: ๐ค We released **online huggingface demo**! Try our [online demo](https://huggingface.co/spaces/bokesyo/MiniCPM_Visual_Document_Retriever_Demo)!
|
| 35 |
|
| 36 |
- 2024-07-14: ๐ We released a **locally deployable Gradio demo** of `Memex`, take a look at [pipeline_gradio.py](https://huggingface.co/RhapsodyAI/minicpm-visual-embedding-v0/blob/main/pipeline_gradio.py). You can build a demo on your PC now!
|
| 37 |
|