Feature Extraction
MLX
Safetensors
qwen3
embeddings
jina
jina-embeddings-v5
mlx-my-repo
4-bit precision
Instructions to use aigentic/jina-embeddings-v5-text-small-classification-mlx-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use aigentic/jina-embeddings-v5-text-small-classification-mlx-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download aigentic/jina-embeddings-v5-text-small-classification-mlx-mlx-4Bit --local-dir jina-embeddings-v5-text-small-classification-mlx-mlx-4Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
aigentic/jina-embeddings-v5-text-small-classification-mlx-mlx-4Bit
The Model aigentic/jina-embeddings-v5-text-small-classification-mlx-mlx-4Bit was converted to MLX format from jinaai/jina-embeddings-v5-text-small-classification-mlx using mlx-lm version 0.31.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("aigentic/jina-embeddings-v5-text-small-classification-mlx-mlx-4Bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
- Downloads last month
- 45
Model size
0.6B params
Tensor type
U32
·
F16 ·
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for aigentic/jina-embeddings-v5-text-small-classification-mlx-mlx-4Bit
Base model
Qwen/Qwen3-0.6B-Base Finetuned
jinaai/jina-embeddings-v5-text-small