Downloads · 30 days
11
3% of all-time downloads
pplx-embed-v1-4b-bnb-4bit-nf4-dq
manu02/pplx-embed-v1-4b-bnb-4bit-nf4-dq
pplx-embed-v1-4b-bnb-4bit-nf4-dq is a feature extraction model from manu02. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as apache-2.0.
This model is a 4-bit quantized version of the original perplexity-ai/pplx-embed-v1-4b model, optimized for reduced memory usage while maintaining performance.
All-time downloads
427
Public
Parameters
4.1B
3.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.4 GB · 100%
Parameter types
How the weights are stored.
U83.7B · 91%
Base models
Model card
From the Hugging Face model README
pplx-embed-v1-4b (Quantized)
Description
This model is a 4-bit quantized version of the original perplexity-ai/pplx-embed-v1-4b model, optimized for reduced memory usage while maintaining performance.
Quantization Details
- Quantization Type: 4-bit
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
- bnb_4bit_quant_storage: uint8
- Original Footprint: 16089.87 MB (FLOAT32)
- Quantized Footprint: 3373.27 MB (UINT8)
- Memory Reduction: 79.0%
Usage
from transformers import AutoModel, AutoTokenizer
model_name = "pplx-embed-v1-4b-bnb-4bit-nf4"
model = AutoModel.from_pretrained(
"manu02/pplx-embed-v1-4b-bnb-4bit-nf4",
)
tokenizer = AutoTokenizer.from_pretrained("manu02/pplx-embed-v1-4b-bnb-4bit-nf4", use_fast=True)
- Task
- Feature Extraction
- Library
- transformers
- Type
- bidirectional_pplx_qwen3
- License
- apache-2.0
- Languages
- en
- Created
- Mar 2, 2026
- Updated
- Mar 2, 2026