finance-gemma-300m-emb
1
—
by
yasserrmd
Embedding Model
OTHER
1705.00652B params
New
1 downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
3811GB+ RAM
Mobile
Laptop
Server
Quick Summary
SentenceTransformer based on google/embeddinggemma-300m This is a sentence-transformers model finetuned from google/embeddinggemma-300m.
Device Compatibility
Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
1588GB+ RAM
Training Data Analysis
🟡 Average (4.3/10)
Researched training datasets used by finance-gemma-300m-emb with quality assessment
Specialized For
general
science
multilingual
reasoning
Training Datasets (3)
common crawl
🔴 2.5/10
general
science
Key Strengths
- •Scale and Accessibility: At 9.5+ petabytes, Common Crawl provides unprecedented scale for training d...
- •Diversity: The dataset captures billions of web pages across multiple domains and content types, ena...
- •Comprehensive Coverage: Despite limitations, Common Crawl attempts to represent the broader web acro...
Considerations
- •Biased Coverage: The crawling process prioritizes frequently linked domains, making content from dig...
- •Large-Scale Problematic Content: Contains significant amounts of hate speech, pornography, violent c...
wikipedia
🟡 5/10
science
multilingual
Key Strengths
- •High-Quality Content: Wikipedia articles are subject to community review, fact-checking, and citatio...
- •Multilingual Coverage: Available in 300+ languages, enabling training of models that understand and ...
- •Structured Knowledge: Articles follow consistent formatting with clear sections, allowing models to ...
Considerations
- •Language Inequality: Low-resource language editions have significantly lower quality, fewer articles...
- •Biased Coverage: Reflects biases in contributor demographics; topics related to Western culture and ...
arxiv
🟡 5.5/10
science
reasoning
Key Strengths
- •Scientific Authority: Peer-reviewed content from established repository
- •Domain-Specific: Specialized vocabulary and concepts
- •Mathematical Content: Includes complex equations and notation
Considerations
- •Specialized: Primarily technical and mathematical content
- •English-Heavy: Predominantly English-language papers
Explore our comprehensive training dataset analysis
View All DatasetsCode Examples
Usagebash
pip install -U sentence-transformersUsagepython
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("yasserrmd/finance-gemma-300m-emb")
# Run inference
queries = [
"Why is there a positive risk-free interest rate, even for investments considered to have no risk, like government bonds?",
]
documents = [
'The interest rate serves two purposes: compensating for risk and rewarding delayed consumption. A positive risk-free rate exists due to the concept of time preference. Generally, individuals prefer consuming now rather than later. To incentivize people to save and invest in risk-free assets, such as government bonds, instead of immediate consumption, a positive interest rate is offered. This interest acts as compensation for deferring gratification.\n\nIn the case of negative interest rates, which are unconventional, it indicates that market participants are more inclined to save for the future despite losing money, possibly due to uncertainties or concerns about the economic outlook. This behavior contradicts the classical economic assumption that people generally prefer immediate consumption over saving, especially when there are no risks involved.',
'The simultaneous implementation of austerity measures and quantitative easing can be understood through the distinction between fiscal and monetary policy. Austerity measures are part of fiscal policy, which is determined by the government (in the case of the UK, Parliament) and involves adjusting spending and taxation to influence the economy. On the other hand, quantitative easing is a monetary policy tool employed by the central bank (in this case, the Bank of England). The central bank has the authority to create new money and use it to purchase financial assets, thus injecting liquidity into the economy.\n\nWhile these two policies may appear contradictory, they operate in separate domains and have different targets. Austerity is often implemented to reduce government deficits and debt, whereas quantitative easing aims to stimulate lending, boost economic activity, and prevent a deflationary spiral. Since they are controlled by separate entities with distinct objectives, it is possible for them to coexist, even if their effects may not always be complementary.',
'\nIn a sigma bond, the electron density is concentrated directly between the two atoms, while in a pi bond, the electron density is concentrated above and below the plane of the two atoms. This difference in electron density distribution results in different bond strengths. Sigma bonds are stronger than pi bonds because they have greater overlap and, therefore, more electron density between the two atoms.\n\nHere are some examples of sigma and pi bonds:\n\n* The C-H bond in methane is a sigma bond.\n* The C=C bond in ethene is a pi bond.\n* The N≡N bond in nitrogen gas is a triple bond, consisting of one sigma bond and two pi bonds.\n####\nSigma and pi bonds form through the overlap of atomic orbitals. A sigma bond is formed when two atomic orbitals overlap head-to-head, while a pi bond is formed when two atomic orbitals overlap sideways. Sigma bonds are stronger than pi bonds because they have greater overlap.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.7866, -0.1002, -0.0356]])Deploy This Model
Production-ready deployment in minutes
Together.ai
Instant API access to this model
Production-ready inference API. Start free, scale to millions.
Try Free APIReplicate
One-click model deployment
Run models in the cloud with simple API. No DevOps required.
Deploy NowDisclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.