Sentence Similarity
sentence-transformers
Safetensors
Transformers
MLX
English
bert
feature-extraction
text-embeddings-inference
Instructions to use thoddnn/all-MiniLM-L6-v2-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use thoddnn/all-MiniLM-L6-v2-4bit with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("thoddnn/all-MiniLM-L6-v2-4bit") 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 thoddnn/all-MiniLM-L6-v2-4bit with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("thoddnn/all-MiniLM-L6-v2-4bit") model = AutoModel.from_pretrained("thoddnn/all-MiniLM-L6-v2-4bit") - MLX
How to use thoddnn/all-MiniLM-L6-v2-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir all-MiniLM-L6-v2-4bit thoddnn/all-MiniLM-L6-v2-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
| [ | |
| { | |
| "idx": 0, | |
| "name": "0", | |
| "path": "", | |
| "type": "sentence_transformers.models.Transformer" | |
| }, | |
| { | |
| "idx": 1, | |
| "name": "1", | |
| "path": "1_Pooling", | |
| "type": "sentence_transformers.models.Pooling" | |
| }, | |
| { | |
| "idx": 2, | |
| "name": "2", | |
| "path": "2_Normalize", | |
| "type": "sentence_transformers.models.Normalize" | |
| } | |
| ] |