Sentence Similarity
sentence-transformers
ONNX
Safetensors
Transformers
Transformers.js
English
nomic_bert
feature-extraction
mteb
custom_code
Eval Results (legacy)
Eval Results
text-embeddings-inference
Instructions to use nomic-ai/nomic-embed-text-v1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use nomic-ai/nomic-embed-text-v1.5 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("nomic-ai/nomic-embed-text-v1.5", trust_remote_code=True) sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use nomic-ai/nomic-embed-text-v1.5 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("nomic-ai/nomic-embed-text-v1.5", trust_remote_code=True) model = AutoModel.from_pretrained("nomic-ai/nomic-embed-text-v1.5", trust_remote_code=True, device_map="auto") - Transformers.js
How to use nomic-ai/nomic-embed-text-v1.5 with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('sentence-similarity', 'nomic-ai/nomic-embed-text-v1.5'); - Notebooks
- Google Colab
- Kaggle
Published ONNX lacks RoPE scaling, effectively capped at 2048 tokens not 8192
#61 opened 3 days ago
by
akshay-bhardwaj
Does pinning nomic-embed-text-v1.5 also pin nomic-bert-2048?
2
#60 opened 20 days ago
by
CyberNativeAI
Nomic Embed — great quality, but can we get it smaller for mobile?
#59 opened about 2 months ago
by
3morixd
Duplicate Field "max_position_embeddings" Bug
👍 2
#58 opened 3 months ago
by
333i
Standardize config.json for native Transformers integration
2
#56 opened 5 months ago
by
SonnyCoops
Add evaluation results for model nomic-ai/nomic-embed-text-v1.5 revision b0753ae76394dd36bcfb912a46018088bca48be0
#55 opened 6 months ago
by
Samoed
Request: DOI
#54 opened about 1 year ago
by
techoraye
REST API for Windows Command.exe
#52 opened about 1 year ago
by
sturodgers
What is the actual context size of nomic embed text?
#51 opened about 1 year ago
by
carlttt
Request: DOI
#50 opened about 1 year ago
by
Thompoth
How to load nomic-ai/nomic-embed-text-v1.5 without connect to internet?
1
#48 opened over 1 year ago
by
keyuchen2019
Supposed to be same or better than v1?
2
#44 opened over 1 year ago
by
persijano
I wish to tokenize the text, before submitting to the model, does this model provide API to tokenize?
#42 opened over 1 year ago
by
JLouisBiz
Wrong model name used in code examples
#41 opened over 1 year ago
by
satorean
Poor performance for long texts
#40 opened over 1 year ago
by
satorean
No attribute 'NomicBertConfig' today due to https://huggingface.co/nomic-ai/nomic-bert-2048/commit/ba22e9d89df6236d83c3daa26cc8dd78a130c3f2
1
#38 opened over 1 year ago
by
lbwavebo-uber
Slow inference performance when using nomic-embed-text-v1.5
5
#34 opened almost 2 years ago
by
umesh-c
how to embed other language documents
1
#31 opened about 2 years ago
by
mahyagh
Can this model be quantized using bitsandbytes or some other method?
#30 opened about 2 years ago
by
RonanMcGovern
Mean pooling with transformers
#26 opened about 2 years ago
by
Miheer29
Rotary Scaling Factor of 4 for 8k context (Do not merge)
1
#23 opened about 2 years ago
by
nbroad
[AUTOMATED] Model Memory Requirements
#15 opened over 2 years ago
by
model-sizer-bot