---
title: tasksource-ModernBERT-base-embed-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/tasksource-ModernBERT-base-embed-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/tasksource-ModernBERT-base-embed-bf16.md"
repository: mlx-community/tasksource-ModernBERT-base-embed-bf16
last_updated: 2025-04-02
pipeline_tag: sentence-similarity
tasks:
  - sentence-similarity
model_type:
  - modernbert
architectures:
  - ModernBertModel
base_model:
  - answerdotai/ModernBERT-base
base_model_relation: finetune
parameters: 149.0M
tensor_type:
  - BF16
library_name:
  - sentence-transformers
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task emb"
  - "vllm 0.9.2"
downloads: 475
stars: 0
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - "dataset_size:6661966"
  - "loss:MultipleNegativesRankingLoss"
  - "loss:CachedMultipleNegativesRankingLoss"
  - "loss:SoftmaxLoss"
  - "loss:AnglELoss"
  - "loss:CoSENTLoss"
  - "loss:CosineSimilarityLoss"
  - mlx
---

# tasksource-ModernBERT-base-embed-bf16

> tasksource-ModernBERT-base-embed-bf16 - mlx-community 在 ModelScope 开源的模型。mlx-community/tasksource-ModernBERT-base-embed-bf16

mlx-community/tasksource-ModernBERT-base-embed-bf16 是 ModelScope 魔搭社区上的 149.0M 参数sentence-similarity模型，基于 answerdotai/ModernBERT-base 构建，可用 deploy_task emb、vllm 0.9.2 部署。

- **Repository**: mlx-community/tasksource-ModernBERT-base-embed-bf16
- **Tasks**: sentence-similarity
- **Parameters**: 149.0M
- **Base model**: answerdotai/ModernBERT-base
- **Inference backends**: deploy_task emb, vllm 0.9.2
- **Tags**: sentence-transformers, sentence-similarity, feature-extraction, generated_from_trainer, dataset_size:6661966, loss:MultipleNegativesRankingLoss, loss:CachedMultipleNegativesRankingLoss, loss:SoftmaxLoss, loss:AnglELoss, loss:CoSENTLoss, loss:CosineSimilarityLoss, mlx
- **Downloads**: 475
- **Stars**: 0
- **Last updated**: 2025-04-02

Source: https://www.modelscope.cn/models/mlx-community/tasksource-ModernBERT-base-embed-bf16

---

# mlx-community/tasksource-ModernBERT-base-embed-bf16

The Model [mlx-community/tasksource-ModernBERT-base-embed-bf16](https://huggingface.co/mlx-community/tasksource-ModernBERT-base-embed-bf16) was converted to MLX format from [tasksource/ModernBERT-base-embed](https://huggingface.co/tasksource/ModernBERT-base-embed) using mlx-lm version **0.0.3**.

## Use with mlx

```bash
pip install mlx-embeddings
```

```python
from mlx_embeddings import load, generate
import mlx.core as mx

model, tokenizer = load("mlx-community/tasksource-ModernBERT-base-embed-bf16")

# 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)


```