Hugging Face's logo

optimum
/
clip-vit-base-patch32-image-classification-neuronx

clip
Model card Files
xet
Community
clip-vit-base-patch32-image-classification-neuronx
File size: 1,342 Bytes 
84f70b3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
 
{
  "_attn_implementation_autoset": true,
  "_name_or_path": "/tmp/tmp7nwl42_l",
  "architectures": [
    "CLIPModel"
  ],
  "initializer_factor": 1.0,
  "logit_scale_init_value": 2.6592,
  "model_type": "clip",
  "neuron": {
    "auto_cast": "matmul",
    "auto_cast_type": "bf16",
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.16.372.0+4a9b2326",
    "disable_fallback": false,
    "disable_fast_relayout": false,
    "dynamic_batch_size": false,
    "inline_weights_to_neff": true,
    "input_names": [
      "pixel_values"
    ],
    "model_type": "clip",
    "optlevel": "2",
    "output_attentions": false,
    "output_hidden_states": false,
    "output_names": [
      "logits"
    ],
    "static_height": 224,
    "static_image_batch_size": 1,
    "static_num_channels": 3,
    "static_sequence_length": 77,
    "static_text_batch_size": 2,
    "static_width": 224,
    "tensor_parallel_size": 1
  },
  "projection_dim": 512,
  "task": "image-classification",
  "text_config": {
    "bos_token_id": 0,
    "dropout": 0.0,
    "eos_token_id": 2,
    "model_type": "clip_text_model",
    "torch_dtype": "float32"
  },
  "torch_dtype": "float32",
  "torchscript": true,
  "transformers_version": "4.49.0",
  "vision_config": {
    "dropout": 0.0,
    "model_type": "clip_vision_model",
    "torch_dtype": "float32"
  }
}