jinaai
/

jina-clip-v2

Model card Files Files and versions

Resources

View closed (30)

encode_image returns embeddings with NaN values in Transformers 5

#61 opened about 2 months ago by

Dependencies while exporting into ONNX format.

#59 opened 4 months ago by

Using task (LoRA) with ONNX model?

#58 opened 7 months ago by

Use text and image encoder separately with onnxruntime

#57 opened 10 months ago by

Pointer argument (at 0) cannot be accessed from Triton (cpu tensor?)

#56 opened 12 months ago by

Blocking access to onnx backend?

#55 opened 12 months ago by

'JinaCLIPConfig' object has no attribute 'num_attention_heads'

#54 opened 12 months ago by

Inconsistent image processing times

#53 opened 12 months ago by

When running the sample locally, an error was reported：AttributeError: 'EVAVisionTransformer' object has no attribute '_initialize_weights'

#52 opened 12 months ago by

how to load the jina-clip-v2 model offline? help me plz!!

#51 opened about 1 year ago by

Failed to load the downloaded model locally

#50 opened about 1 year ago by

Encountering issues while deploying Jina-CLIP v2 on AWS using jina-sagemaker.

#49 opened about 1 year ago by

Will you release the fine-tuning code as open source?

#48 opened about 1 year ago by

gguf format please?

#46 opened about 1 year ago by

Using a slow image processor as `use_fast` is unset - Transformers issue

#45 opened about 1 year ago by

ValueError: Invalid image type. Expected either PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray, but got <class 'list'>.

#44 opened about 1 year ago by

Running on Apple Silicon with GPU

#43 opened about 1 year ago by

do you have 224x224 or 386x386 pretrained clip model?

#42 opened about 1 year ago by

Ollama use?

#41 opened about 1 year ago by

Does “multilingual MSCOCO” refer to “XTD”?

#38 opened over 1 year ago by

Onnx clip-v2 inferrence q4,uint8 speed slower than fp16

#37 opened over 1 year ago by

Loading jina-clip-v2 extremely slow

#36 opened over 1 year ago by

The issue of VRAM usage in image extraction

#35 opened over 1 year ago by

Jina Clip V2 Encode_image latency is proportional to batch size

#33 opened over 1 year ago by

Jina Clip V2: Inconsistent Embeddings

#32 opened over 1 year ago by

Dose this model support mixed-modality input?

#29 opened over 1 year ago by

ValueError: JinaCLIPModel does not support Flash Attention 2.0 yet

#27 opened over 1 year ago by

Exception: data did not match any variant of untagged enum PyPreTokenizerTypeWrapper at line 83 column 3

#25 opened over 1 year ago by

Transformers.js error: can't find model.onnx_data file

#22 opened over 1 year ago by

ValueError: class 'jina_clip_v2.configuration_clip.JinaCLIPConfig'>

#21 opened over 1 year ago by

onnx use pixel_values = np.random.rand(0, 3, 512, 512).astype(np.float32) will cause onnx warning

#15 opened over 1 year ago by