Add files using upload-large-folder tool
Browse files- config.json +46 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +32 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CLIPModel"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "float32",
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"logit_scale_init_value": 2.6592,
|
| 8 |
+
"model_type": "clip",
|
| 9 |
+
"projection_dim": 512,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"dropout": 0.0,
|
| 13 |
+
"dtype": "float32",
|
| 14 |
+
"hidden_act": "gelu",
|
| 15 |
+
"hidden_size": 512,
|
| 16 |
+
"initializer_factor": 1.0,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 2048,
|
| 19 |
+
"layer_norm_eps": 1e-05,
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "clip_text_model",
|
| 22 |
+
"num_attention_heads": 8,
|
| 23 |
+
"num_hidden_layers": 12,
|
| 24 |
+
"projection_dim": 512,
|
| 25 |
+
"vocab_size": 49408
|
| 26 |
+
},
|
| 27 |
+
"transformers_version": "4.57.3",
|
| 28 |
+
"vision_config": {
|
| 29 |
+
"attention_dropout": 0.0,
|
| 30 |
+
"dropout": 0.0,
|
| 31 |
+
"dtype": "float32",
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_size": 768,
|
| 34 |
+
"image_size": 224,
|
| 35 |
+
"initializer_factor": 1.0,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"intermediate_size": 3072,
|
| 38 |
+
"layer_norm_eps": 1e-05,
|
| 39 |
+
"model_type": "clip_vision_model",
|
| 40 |
+
"num_attention_heads": 12,
|
| 41 |
+
"num_channels": 3,
|
| 42 |
+
"num_hidden_layers": 12,
|
| 43 |
+
"patch_size": 32,
|
| 44 |
+
"projection_dim": 512
|
| 45 |
+
}
|
| 46 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a732f8ee2be5650b32a17373fa546c61a76c36a8267eea233d5dee5cf676754
|
| 3 |
+
size 606047556
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"data_format": "channels_first",
|
| 7 |
+
"default_to_square": false,
|
| 8 |
+
"device": null,
|
| 9 |
+
"disable_grouping": null,
|
| 10 |
+
"do_center_crop": true,
|
| 11 |
+
"do_convert_rgb": true,
|
| 12 |
+
"do_normalize": true,
|
| 13 |
+
"do_pad": null,
|
| 14 |
+
"do_rescale": true,
|
| 15 |
+
"do_resize": true,
|
| 16 |
+
"image_mean": [
|
| 17 |
+
0.48145466,
|
| 18 |
+
0.4578275,
|
| 19 |
+
0.40821073
|
| 20 |
+
],
|
| 21 |
+
"image_processor_type": "CLIPImageProcessorFast",
|
| 22 |
+
"image_std": [
|
| 23 |
+
0.26862954,
|
| 24 |
+
0.26130258,
|
| 25 |
+
0.27577711
|
| 26 |
+
],
|
| 27 |
+
"input_data_format": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"processor_class": "CLIPProcessor",
|
| 30 |
+
"resample": 3,
|
| 31 |
+
"rescale_factor": 0.00392156862745098,
|
| 32 |
+
"return_tensors": null,
|
| 33 |
+
"size": {
|
| 34 |
+
"shortest_edge": 224
|
| 35 |
+
}
|
| 36 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"49406": {
|
| 5 |
+
"content": "<|startoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"49407": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"bos_token": "<|startoftext|>",
|
| 22 |
+
"clean_up_tokenization_spaces": false,
|
| 23 |
+
"do_lower_case": true,
|
| 24 |
+
"eos_token": "<|endoftext|>",
|
| 25 |
+
"errors": "replace",
|
| 26 |
+
"extra_special_tokens": {},
|
| 27 |
+
"model_max_length": 512,
|
| 28 |
+
"pad_token": "<|endoftext|>",
|
| 29 |
+
"processor_class": "CLIPProcessor",
|
| 30 |
+
"tokenizer_class": "CLIPTokenizer",
|
| 31 |
+
"unk_token": "<|endoftext|>"
|
| 32 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|