HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

siglip-so400m-patch14-384

google/siglip-so400m-patch14-384

kind
original
quant
bf16 (16-bit)
family
misc
modality
zero-shot-image-classification
root model
google/siglip-so400m-patch14-384
provider
google
license
apache-2.0
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
2,245,567
likes
681
created
—
last modified
2024-09-26T08:21:46+00:00 (2024)
huggingface
https://huggingface.co/google/siglip-so400m-patch14-384
tags
transformerssafetensorssiglipzero-shot-image-classificationvisionarxiv:2303.15343arxiv:2305.13035arxiv:2209.06794license:apache-2.0endpoints_compatibleregion:us

Benchmark scores (0)

no scores extracted for this variant.

Discussions (10)

titleauthorstatuscommentstype
readAngel522776draft0disc
Is SiglipImageProcessor configured correctly?karbyopen0disc
Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory D:/comfyui/models/clip\siglip-so400m-patch14-384danzjhioajopen0disc
upload fast tokenizer.jsonitazapmerged0disc
How to set grad checkpointing?mactavish91open0disc
Probability always showing zerosans07-jdopen0disc
Why is the image size designed to be 384, whereas the patch size is designed to be 14, when 384 is not divisible by 14?zhongyi1997cnopen0disc
hidden sizesVictorSanhclosed0disc
Output features are different compared to timmmobichamclosed0disc
Model performance is not adequate.talrejanikhilclosed0disc
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.