ModelPrésentéExterne

Surgical Instruments LoRA Adapter

This repository contains a LoRA adapter for OpenCLIP vision inference.

Sourcehuggingface.co/mounkie/surgical_instruments-lora-adapter/tree/0e681afa3e1bdc3ac1b941a7dbc9e1a9cca03bcb

TypeLoRAModèle de baselaion/CLIP-ViT-B-32-DataComp.XL-s13B-b90KVersionadapter_modelCClasse

Source du modèle

Type: LoRA
Taille du fichier: 2,82 MB
Modèle de base: laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K
Version: vadapter_model
Mis à jour: 22 oct. 2026
Source: Hugging Face

Description de la source

PEFT LoRA Adapter

This repository contains a LoRA adapter for OpenCLIP vision inference.

Base model: open-clip:laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K
Adapter target: visual.transformer
Task: image_embedding

Usage

import open_clip
import torch
from peft import PeftModel

MODEL_NAME = 'hf-hub:laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K'
ADAPTER_REPO = 'mounkie/surgical_instruments-lora-adapter'

model, _, preprocess = open_clip.create_model_and_transforms(MODEL_NAME)
model.visual.transformer = PeftModel.from_pretrained(
    model.visual.transformer,
    ADAPTER_REPO,
)
model.eval()

# image = preprocess(pil_image).unsqueeze(0)
# with torch.no_grad():
#     image_features = model.encode_image(image)
#     image_features = image_features / image_features.norm(dim=-1, keepdim=True)

Sources

1 source

Hugging FacePrincipalVersion 0e681afa3e1bdc3ac1b941a7dbc9e1a9cca03bcb

huggingface.co/mounkie/surgical_instruments-lora-adapter/tree/0e681afa3e1bdc3ac1b941a7dbc9e1a9cca03bcb

Vérifié 22 oct.

Artefacts du modèle

1 artefact

adapter_model.safetensors

safetensors · 2,82 MB · SHA-256 6d009ee7694c…7109 · Hugging Face

Télécharger

Extraits de sources

2 extraits

Readme5 aoûthuggingface.co/mounkie/surgical_instruments-lora-adapter

--- library_name: peft pipeline_tag: image-feature-extraction tags: - peft - lora - open-clip - image-feature-extraction base_model: laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K --- # PEFT LoRA Adapter This repository contains a LoRA adapter for OpenCLIP vision inference. - Base model: `open-clip:laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K` - Adapter target: `visual.transformer` - Task: `image_embedding` ## Usage ```python import open_clip import torch from peft import PeftModel MODEL_NAME = 'hf-hub:laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K' ADAPTER_REPO = 'mounkie/surgical_instruments-lora-adapter' model, _, preprocess = open_clip.create_model_and_transforms(MODEL_NAME) model.visual.transformer = PeftModel.from_pretrained( model.visual.transformer, ADAPTER_REPO, ) model.eval() # image = preprocess(pil_image).unsqueeze(0) # with torch.no_grad(): # image_features = model.encode_image(image) # image_features = image_features / image_features.norm(dim=-1, keepdim=True) ```

Note5 aoûthuggingface.co/mounkie/surgical_instruments-lora-adapter

Source context: 5 downloads · 0 likes · Pipeline image-feature-extraction · Library peft · Repo mounkie/surgical_instruments-lora-adapter