Text Ranking
Transformers
Safetensors
multilingual
t5gemma2
text2text-generation
reranker
encoder-decoder
FBNL
Retrieval
RAG
Instructions to use KaLM-Embedding/KaLM-Reranker-V1-Large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KaLM-Embedding/KaLM-Reranker-V1-Large with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("KaLM-Embedding/KaLM-Reranker-V1-Large") model = AutoModelForMultimodalLM.from_pretrained("KaLM-Embedding/KaLM-Reranker-V1-Large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 56eff54f870bf5f17a5ba8d65a0aeec6329d9f2bede7d63f17280dbe80490537
- Size of remote file:
- 15 GB
- SHA256:
- 94c59b9ce11b0f36c456419a3e43c9ca9c3a9ab4c86c1f97e51fdb896317e002
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.