ModernBert
Collection
16 items • Updated • 2
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("mlx-community/answerdotai-ModernBERT-Large-Instruct-8bit")
model = AutoModelForMaskedLM.from_pretrained("mlx-community/answerdotai-ModernBERT-Large-Instruct-8bit", device_map="auto")Quick Links
mlx-community/answerdotai-ModernBERT-Large-Instruct-8bit
The Model mlx-community/answerdotai-ModernBERT-Large-Instruct-8bit was converted to MLX format from answerdotai/ModernBERT-Large-Instruct using mlx-lm version 0.0.3.
Use with mlx
pip install mlx-embeddings
from mlx_embeddings import load, generate
import mlx.core as mx
model, tokenizer = load("mlx-community/answerdotai-ModernBERT-Large-Instruct-8bit")
# For text embeddings
output = generate(model, processor, texts=["I like grapes", "I like fruits"])
embeddings = output.text_embeds # Normalized embeddings
# Compute dot product between normalized embeddings
similarity_matrix = mx.matmul(embeddings, embeddings.T)
print("Similarity matrix between texts:")
print(similarity_matrix)
- Downloads last month
- 17
Model size
0.4B params
Tensor type
F16
·
U32 ·
Hardware compatibility
Log In to add your hardware
Quantized
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="mlx-community/answerdotai-ModernBERT-Large-Instruct-8bit")