sentence-transformers How to use Maximgolubov/legal-ft-2 with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("Maximgolubov/legal-ft-2")
sentences = [
"What is the total cost to process 68,000 images based on the provided token calculations?",
"One way to think about these models is an extension of the chain-of-thought prompting trick, first explored in the May 2022 paper Large Language Models are Zero-Shot Reasoners.\nThis is that trick where, if you get a model to talk out loud about a problem it’s solving, you often get a result which the model would not have achieved otherwise.\no1 takes this process and further bakes it into the model itself. The details are somewhat obfuscated: o1 models spend “reasoning tokens” thinking through the problem that are not directly visible to the user (though the ChatGPT UI shows a summary of them), then outputs a final result.",
"Each photo would need 260 input tokens and around 100 output tokens.\n260 * 68,000 = 17,680,000 input tokens\n17,680,000 * $0.0375/million = $0.66\n100 * 68,000 = 6,800,000 output tokens\n6,800,000 * $0.15/million = $1.02\nThat’s a total cost of $1.68 to process 68,000 images. That’s so absurdly cheap I had to run the numbers three times to confirm I got it right.\nHow good are those descriptions? Here’s what I got from this command:\nllm -m gemini-1.5-flash-8b-latest describe -a IMG_1825.jpeg",
"So far, I think they’re a net positive. I’ve used them on a personal level to improve my productivity (and entertain myself) in all sorts of different ways. I think people who learn how to use them effectively can gain a significant boost to their quality of life.\nA lot of people are yet to be sold on their value! Some think their negatives outweigh their positives, some think they are all hot air, and some even think they represent an existential threat to humanity.\nThey’re actually quite easy to build\nThe most surprising thing we’ve learned about LLMs this year is that they’re actually quite easy to build."
]
embeddings = model.encode(sentences)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4] 
