Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
Generated from Trainer
dataset_size:1416
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use marroyo777/bge-99GPT-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use marroyo777/bge-99GPT-v1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("marroyo777/bge-99GPT-v1") sentences = [ "Who wrote the blog Sprint 7: Iterating upon iterations?", "Title: From Insights to Impact: 99P Labs Collaborates with BDAA to Foster Data Visualization Talent\nPublished: March, 2023\nAuthor(s): Ryan Lingo\nClaps: 0\nComments: 0\nWord Count: 1537\nURL: https://medium.com/99p-labs/from-insights-to-impact-99p-labs-collaborates-with-bdaa-to-foster-data-visualization-talent-26e22a76d1df\n\nIn the spring of 2023, 99P Labs sponsored a data visualization challenge in collaboration with BDAA, the Big Data and Analytics Association at Ohio State University. The challenge lasted two weeks and began with a kickoff event where the 99P Labs team went to the weekly Tuesday BDAA meeting and laid out the motivation and starting guardrails for the challenge. The challenge allowed 99P Labs to connect with the next generation of data professionals and support their growth and development. The data visualization challenge was open to all BDAA members and lasted two weeks. The teams used a wide range of tools and software to create their visualizations and dashboards, including Streamlit, Plotly Dash, and Tableau. The winning entries were highlighted, and the challenge was a valuable experience for 99P Labs. The challenge was not just an opportunity for the students to learn, but it was also an opportunity for 99P Labs to connect with the next generation of data professionals and help build their developer community. The collaboration with BDAA was strengthened, and they look forward to continuing this collaboration in the future.", "Title: Sprint 7: Iterating upon iterations\nPublished: October, 2023\nAuthor(s): 2023 99P Labs x CMU MHCI Capstone Team\nClaps: 24\nComments: 0\nWord Count: 985\nURL: https://medium.com/99p-labs/sprint-7-iterating-upon-iterations-34cc621a5aeb\n\nThe 99P Labs x CMU MHCI Capstone Team is part of the Master of Human-Computer Interaction (MHCI) program at Carnegie Mellon University. The team started off with a blank canvas and ran design sessions with 3 Gen Z participants to shape their mobile mentor to fit their learning needs. They found that the activities people wanted to perform in cars fell under a few main hierarchies and came up with a set of 3 scenarios to test out the different roles that Gen Zers expect from the mobile mentor. The team then moved from more generative to evaluative testing and decided to focus on the tutor scenario, making use of the unique moving environment of a vehicle. They also made use of their clients' expertise in vehicle HCI design to conduct testing sessions. The team is looking forward to shaping the future of learning on-the-go in their last few iterations.", "Title: 99P Labs 2022 Data I/O Recap\nPublished: November, 2022\nAuthor(s): Ryan Lingo\nClaps: 259\nComments: 0\nWord Count: 1021\nURL: https://medium.com/99p-labs/99p-labs-2022-data-i-o-recap-7c710fbe28e6\n\nThe blog post discusses the 99P Labs 2022 Data I/O Recap, which took place at The Ohio State University. The event included 50 students participating in 12 teams, with 99P Labs sponsoring and offering a challenge for the participants. Despite varying skill levels, the atmosphere remained friendly and inclusive. The event allowed for more personal interaction and submissions from all teams, resulting in impressive insights and visuals. The winning teams were determined by a team of 99P Labs and OSU faculty. Overall, the author expresses their enjoyment and the inspiring energy of the event. For more information, readers are encouraged to visit the 99P Labs blog post." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Welcome to the community
The community tab is the place to discuss and collaborate with the HF community!