tiny clip text 2

Providerpeft-internal-testing
Categoryimage-text-retrieval
LicenseApache-2.0
Downloads1.9M
Stars0

Overview

Tiny CLIP Text 2 is a lightweight image-text retrieval model designed for developers who need efficient embedding generation without the overhead of massive vision-language transformers. By optimizing the text-encoder pipeline, it allows for rapid semantic mapping between textual queries and visual assets, making it ideal for edge deployments or high-throughput indexing tasks. Unlike full-scale CLIP models, this version prioritizes a smaller footprint, reducing latency in search-and-retrieval workflows while maintaining the core ability to align multi-modal representations. It integrates easily into existing vector databases for implementing visual search or automated tagging systems where resource constraints are a primary concern.

Highlights

  • Optimized for low-latency image-text retrieval tasks
  • Low memory footprint ideal for edge deployment
  • Seamless integration with vector search databases
  • Apache-2.0 license for flexible commercial use

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("peft-internal-testing/tiny-clip-text-2")
tokenizer = AutoTokenizer.from_pretrained("peft-internal-testing/tiny-clip-text-2")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download peft-internal-testing/tiny-clip-text-2

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download peft-internal-testing/tiny-clip-text-2 config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('peft-internal-testing/tiny-clip-text-2')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/peft-internal-testing/tiny-clip-text-2

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/peft-internal-testing/tiny-clip-text-2

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('peft-internal-testing/tiny-clip-text-2')
tokenizer = AutoTokenizer.from_pretrained('peft-internal-testing/tiny-clip-text-2')
View official source
Join our Telegram