Instructions to use 0xFarzad/embeddinggemma-graph-instructions-hard-negatives-final with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0xFarzad/embeddinggemma-graph-instructions-hard-negatives-final with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("0xFarzad/embeddinggemma-graph-instructions-hard-negatives-final")

sentences = [
    "<ROUTE_START>\n<SEG> ST_1 -> ST_2 <DIR:RIGHT> <LIGHT> <POI: Pie Face / amenity: cafe / cuisine: coffee_shop>\n<SEG> ST_2 -> ST_3 <DIR:STRAIGHT> <POI_RIGHT: amenity: parking> <POI_LEFT: Zoob Zib Aura Thai / amenity: restaurant / cuisine: thai> <POI_LEFT: Pie Face / amenity: cafe / cuisine: coffee_shop> <POI_LEFT: Burgers and Cupcakes / amenity: restaurant / cuisine: burger>\n<SEG> ST_3 -> ST_4 <DIR:STRAIGHT> <POI_RIGHT: amenity: parking> <POI_LEFT: Zoob Zib Aura Thai / amenity: restaurant / cuisine: thai> <POI_LEFT: Burgers and Cupcakes / amenity: restaurant / cuisine: burger> <POI_LEFT: Sergimmo Slumeria / amenity: restaurant / cuisine: italian>\n<SEG> ST_4 -> ST_5 <DIR:STRAIGHT> <POI_RIGHT: amenity: parking> <POI_LEFT: Burgers and Cupcakes / amenity: restaurant / cuisine: burger> <POI_LEFT: Sergimmo Slumeria / amenity: restaurant / cuisine: italian> <POI_LEFT: shop: convenience>\n<SEG> ST_5 -> ST_6 <DIR:STRAIGHT> <LIGHT> <POI_LEFT: Golden City / amenity: restaurant> <POI_LEFT: Deli & Pizzeria / amenity: fast_food / cuisine: pizza>\n<SEG> ST_6 -> ST_7 <DIR:STRAIGHT> <POI_LEFT: Hudson Station Bar and Grill / amenity: restaurant / cuisine: steak_house> <POI_LEFT: Uncle Jack's / amenity: restaurant / cuisine: steak_house>\n<SEG> ST_7 -> ST_8 <DIR:STRAIGHT> <POI_RIGHT: Café Bistro / amenity: fast_food / cuisine: deli,_buffet,_Asian,_salad,_pizza>\n<SEG> ST_8 -> ST_9 <DIR:STRAIGHT> <POI_RIGHT: Café Bistro / amenity: fast_food / cuisine: deli,_buffet,_Asian,_salad,_pizza> <POI_LEFT: Five Guys / amenity: fast_food>\n<ROUTE_END>",
    "Walk to the light where Pie Face may be on the corner and turn right. Pass a parking lot on the right and go through a light. At the following light where Golden City and Deli & Pizzeria may be on the corners turn left. Stop 1/2 down the block next to Cafe Bistro just before Five Guys on the right side.",
    "Go straight past M408 Performing Arts high school then at the intersection where Chaan Teng and take a left.",
    "Walk to the light where Pie Face may be on the corner and turn right. Pass a parking lot on the right and go through a light. At the following light where Golden City and Deli & Pizzeria may be on the corners turn left. Stop 1/2 down the block next to Cafe Bistro just before Five Guys on the right side."
]
embeddings = model.encode(sentences)

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4]

Notebooks
Google Colab
Kaggle

embeddinggemma-graph-instructions-hard-negatives-final / model.safetensors

0xFarzad

Add new SentenceTransformer model

2a2fb28 verified 11 months ago

Download

History Blame Contribute Delete

1.21 GB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 967fa95ae428823627876ecc065cc5466a04240a853ff76dbd5f7c98a3a8b6dc
Size of remote file:: 1.21 GB
SHA256:: 48ced7ca75c35cbc0c2f6e2d2e8d4d034db5fb562580f1928cdfb95dbe89bdda

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.