Instructions to use do2do2/prag with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use do2do2/prag with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("do2do2/prag", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,9 +21,8 @@ This is PRAG, a LLM model trained for multi recommendation tasks and domains. I
|
|
| 21 |
The PRAG model is designed for product recommendation and retrieval tasks. It maps text inputs (queries or item descriptions) to high-dimensional embeddings. The model is optimized using contrastive learning, where the goal is to maximize the cosine similarity between a query and its corresponding relevant item while minimizing similarity with irrelevant items.
|
| 22 |
|
| 23 |
- **Developed by:** @[dodo](https://huggingface.co/do2do2), @[quocdat32461997](https://huggingface.co/tendatngo)
|
| 24 |
-
- **Model type:** LLM
|
| 25 |
- **Language(s) (NLP):** English
|
| 26 |
-
- **Finetuned from model:** LLM Encoder
|
| 27 |
|
| 28 |
### Model Sources [optional]
|
| 29 |
<!-- Provide the basic links for the model. -->
|
|
|
|
| 21 |
The PRAG model is designed for product recommendation and retrieval tasks. It maps text inputs (queries or item descriptions) to high-dimensional embeddings. The model is optimized using contrastive learning, where the goal is to maximize the cosine similarity between a query and its corresponding relevant item while minimizing similarity with irrelevant items.
|
| 22 |
|
| 23 |
- **Developed by:** @[dodo](https://huggingface.co/do2do2), @[quocdat32461997](https://huggingface.co/tendatngo)
|
| 24 |
+
- **Model type:** LLM
|
| 25 |
- **Language(s) (NLP):** English
|
|
|
|
| 26 |
|
| 27 |
### Model Sources [optional]
|
| 28 |
<!-- Provide the basic links for the model. -->
|