Downloads · 30 days
11
17% of all-time downloads
florianhoenicke/medical-1000-64-16-jinaai_jina-embeddings-v2-small-en-1000-gpt-3.5-tur_9062874564
medical-1000-64-16-jinaai_jina-embeddings-v2-small-en-1000-gpt-3.5-tur_9062874564 is a feature extraction model from florianhoenicke. Use it when you need embeddings to search or compare text. It is set up for transformers.
medical-1000-64-16-jinaaijina-embeddings-v2-small-en-1000-gpt-3.5-tur9062874564 is a fine-tuned version of jinaai/jina-embeddings-v2-small-en designed for a specific domain.
Downloads · 30 days
11
17% of all-time downloads
All-time downloads
63
Public
Parameters
32.7M
131 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors131 MB · 99%
From the Hugging Face model README
medical-1000-64-16-jinaai_jina-embeddings-v2-small-en-1000-gpt-3.5-tur_9062874564 is a fine-tuned version of jinaai/jina-embeddings-v2-small-en designed for a specific domain.
This model is designed to support various applications in natural language processing and understanding.
This the dataset for this model can be found here.
This model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started:
from transformers import AutoModel, AutoTokenizer
llm_name = "medical-1000-64-16-jinaai_jina-embeddings-v2-small-en-1000-gpt-3.5-tur_9062874564"
tokenizer = AutoTokenizer.from_pretrained(llm_name)
model = AutoModel.from_pretrained(llm_name)
tokens = tokenizer("Your text here", return_tensors="pt")
embedding = model(**tokens)