Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

shadowlilac
/
omniembed

Sentence Similarity
sentence-transformers
Safetensors
feature-extraction
dense
Generated from Trainer
dataset_size:2083959
loss:MatryoshkaLoss
loss:GeminiEmbedding2NCELoss
Eval Results (legacy)
Model card Files Files and versions
xet
Community

Instructions to use shadowlilac/omniembed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • sentence-transformers

    How to use shadowlilac/omniembed with sentence-transformers:

    from sentence_transformers import SentenceTransformer
    
    model = SentenceTransformer("shadowlilac/omniembed")
    
    sentences = [
        "sulfur dioxide",
        "Recently, we reported on the analysis of polychlorinated biphenyls (PCBs) and chlorinated pesticides in farmed Atlantic salmon (Salmo salar) from Maine, eastern Canada, and Norway, and wild Alaskan Chinook salmon (Oncorhynchus tshawytscha). In this paper, we extend the analysis to polybrominated diphenyl ethers (PBDEs) in these samples. Total PBDE concentrations in the farmed salmon (0.4-1.4ng/g, wet weight, ww) were not significantly different from those in the wild Alaskan Chinook samples (0.4-1.2ng/g, ww), nor were significant differences found among regions. However, significant intra-regional variations in concentrations of total PBDEs and tetra-BDE 47 were observed in the salmon from the Canadian farms (p<0.01). Congener profiles were dominated by BDE-47, followed by the penta-BDEs 99 and 100. PBDE concentrations in the Canadian samples were lower than those reported two years earlier. Removal of skin resulted in no overall reduction in PBDE concentrations in our farmed salmon, and in some cases, PBDE concentrations were higher in skin-off samples. PBDEs were correlated with lipids only in the skinned samples, suggesting that there is greater accumulation and retention of PBDEs in muscle lipids than in skin-associated fat. In skin-on samples, modest correlations were observed between concentrations of PBDEs and PCBs (R(2)=0.47) and mono-ortho PCBs (R(2)=0.50), whereas PBDEs were not correlated with non-ortho PCBs.",
        "We investigated the effect of resistant starch (RS) on markers of colonic protein metabolism. Eleven subjects participated in a randomized crossover study in which they consumed either high-RS (39 +/- 3 g/d, -chi +/- SEM) or low-RS (5 +/- 0.4 g/d) diets for 3 wk. All other macronutrients were kept constant. During the high-RS diet daily excretion of fecal nitrogen increased from 1.84 +/- 0.15 to 2.86 +/- 0.42 g/d (P < 0.01) and excretion of fecal phenols fell from 9.2 +/- 1.4 to 5.3 +/- 0.8 mg/d (P < 0.01). Fecal concentrations of ammonia decreased from 397 +/- 33 to 278 +/- 49 microgram/g (P < 0.01) and phenols decreased from 69 +/- 8 to 39 +/- 10 microgram/g (P < 0.001). Daily output of urinary ammonia, urea, phenols, and total nitrogen did not change significantly, but pH decreased from 6.4 +/- 0.1 to 6.2 +/- 0.1 (P < 0.05) during the high-RS period. These results suggest that RS significantly attenuates the accumulation of potentially harmful byproducts of protein fermentation in the human colon.",
        "The difference between prepaid and postpaid is determined by when you pay for them. With our sim-only plans being prepaid, it means you'll always pay for your 28-day plan upfront on a month to month basis."
    ]
    embeddings = model.encode(sentences)
    
    similarities = model.similarity(embeddings, embeddings)
    print(similarities.shape)
    # [4, 4]
  • Notebooks
  • Google Colab
  • Kaggle
omniembed
283 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
shadowlilac's picture
shadowlilac
Add new SentenceTransformer model
1abef8d verified 2 days ago
  • 1_MultiheadAttentionPooling
    Add new SentenceTransformer model 2 days ago
  • .gitattributes
    1.57 kB
    Add new SentenceTransformer model 2 days ago
  • README.md
    610 kB
    Add new SentenceTransformer model 2 days ago
  • adapter_config.json
    1.14 kB
    Add new SentenceTransformer model 2 days ago
  • adapter_model.safetensors
    193 MB
    xet
    Add new SentenceTransformer model 2 days ago
  • chat_template.jinja
    18.6 kB
    Add new SentenceTransformer model 2 days ago
  • config_sentence_transformers.json
    301 Bytes
    Add new SentenceTransformer model 2 days ago
  • modules.json
    418 Bytes
    Add new SentenceTransformer model 2 days ago
  • processor_config.json
    1.69 kB
    Add new SentenceTransformer model 2 days ago
  • sentence_bert_config.json
    747 Bytes
    Add new SentenceTransformer model 2 days ago
  • tokenizer.json
    32.2 MB
    xet
    Add new SentenceTransformer model 2 days ago
  • tokenizer_config.json
    3.7 kB
    Add new SentenceTransformer model 2 days ago