sentence-transformers How to use zacbrld/MNLP_M3_document_encoder with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("zacbrld/MNLP_M3_document_encoder")
sentences = [
"For example, t ∈ { 0 , 1 , … , N } , N 0 , or {\\mbox{ or }}[0,+\\infty ).} Similarly, a filtered probability space (also known as a stochastic basis) ( Ω , F , { F t } t ≥ 0 , P ) {\\displaystyle \\left(\\Omega ,{\\mathcal {F}},\\left\\{{\\mathcal {F}}_{t}\\right\\}_{t\\geq 0},\\mathbb {P} \\right)} , is a probability space equipped with the filtration { F t } t ≥ 0 {\\displaystyle \\left\\{{\\mathcal {F}}_{t}\\right\\}_{t\\geq 0}} of its σ {\\displaystyle \\sigma } -algebra F {\\displaystyle {\\mathcal {F}}} . A filtered probability space is said to satisfy the usual conditions if it is complete (i.e., F 0 {\\displaystyle {\\mathcal {F}}_{0}} contains all P {\\displaystyle \\mathbb {P} } -null sets) and right-continuous (i.e. F t = F t + := ⋂ s > t F s {\\displaystyle {\\mathcal {F}}_{t}={\\mathcal {F}}_{t+}:=\\bigcap _{s>t}{\\mathcal {F}}_{s}} for all times t {\\displaystyle t} ).It is also useful (in the case of an unbounded index set) to define F ∞ {\\displaystyle {\\mathcal {F}}_{\\infty }} as the σ {\\displaystyle \\sigma } -algebra generated by the infinite union of the F t {\\displaystyle {\\mathcal {F}}_{t}} 's, which is contained in F {\\displaystyle {\\mathcal {F}}}: F ∞ = σ ( ⋃ t ≥ 0 F t ) ⊆ F .",
"These individuals can experience these symptoms from failed attempts of depression like symptoms.Narcissistic personality disorder is characterized as feelings of superiority, a sense of grandiosity, exhibitionism, charming but also exploitive behaviors in the interpersonal domain, success, beauty, feelings of entitlement and a lack of empathy. Those with this disorder often engage in assertive self enhancement and antagonistic self protection. All of these factors can lead an individual with narcissistic personality disorder to manipulate others.",
"{\\displaystyle {\\mathcal {F}}_{\\infty }=\\sigma \\left(\\bigcup _{t\\geq 0}{\\mathcal {F}}_{t}\\right)\\subseteq {\\mathcal {F}}.} A σ-algebra defines the set of events that can be measured, which in a probability context is equivalent to events that can be discriminated, or \"questions that can be answered at time t {\\displaystyle t} \". Therefore, a filtration is often used to represent the change in the set of events that can be measured, through gain or loss of information. A typical example is in mathematical finance, where a filtration represents the information available up to and including each time t {\\displaystyle t} , and is more and more precise (the set of measurable events is staying the same or increasing) as more information from the evolution of the stock price becomes available.",
"Section: Structure and dynamics > Composition. Like microtubules, neurotubules are made up of protein polymers of α-tubulin and β-tubulin, globular proteins that are closely related. They join together to form a dimer, called tubulin. Neurotubules are generally assembled by 13 protofilaments which are polymerized from tubulin dimers. As a tubulin dimer consists of one α-tubulin and one β-tubulin, one end of the neurotubule is exposed with the α-tubulin and the other end with β-tubulin, these two ends contribute to the polarity of the neurotubule – the plus (+) end and the minus (-) end. The β-tubulin subunit is exposed on the plus (+) end. The two ends differ in their growth rate: plus (+) end is the fast-growing end while minus (-) end is the slow-growing end. Both ends have their own rate of polymerization and depolymerization of tubulin dimers, net polymerization causes the assembly of tubulin, hence the length of the neurotubules."
]
embeddings = model.encode(sentences)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4] 
