How to use deepali1021/legal-ft-v0 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("deepali1021/legal-ft-v0") sentences = [ "What new shape of LLM was introduced in the final quarter of 2024, and what were the names of the initial models released?", "17th: AI for Data Journalism: demonstrating what we can do with this stuff right now\n\n22nd: Options for accessing Llama 3 from the terminal using LLM\n\n\n\nMay\n\n8th: Slop is the new name for unwanted AI-generated content\n\n15th: ChatGPT in “4o” mode is not running the new features yet\n\n29th: Training is not the same as chatting: ChatGPT and other LLMs don’t remember everything you say\n\n\n\nJune\n\n6th: Accidental prompt injection against RAG applications\n\n10th: Thoughts on the WWDC 2024 keynote on Apple Intelligence\n\n17th: Language models on the command-line\n\n21st: Building search-based RAG using Claude, Datasette and Val Town\n\n27th: Open challenges for AI engineering\n\n\n\nJuly\n\n14th: Imitation Intelligence, my keynote for PyCon US 2024", "Now that those features are rolling out they’re pretty weak. As an LLM power-user I know what these models are capable of, and Apple’s LLM features offer a pale imitation of what a frontier LLM can do. Instead we’re getting notification summaries that misrepresent news headlines and writing assistant tools that I’ve not found useful at all. Genmoji are kind of fun though.\nThe rise of inference-scaling “reasoning” models\nThe most interesting development in the final quarter of 2024 was the introduction of a new shape of LLM, exemplified by OpenAI’s o1 models—initially released as o1-preview and o1-mini on September 12th.", "Terminology aside, I remain skeptical as to their utility based, once again, on the challenge of gullibility. LLMs believe anything you tell them. Any systems that attempts to make meaningful decisions on your behalf will run into the same roadblock: how good is a travel agent, or a digital assistant, or even a research tool if it can’t distinguish truth from fiction?\nJust the other day Google Search was caught serving up an entirely fake description of the non-existant movie “Encanto 2”. It turned out to be summarizing an imagined movie listing from a fan fiction wiki." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]
