Upload folder using huggingface_hub
Browse files- config.json +2 -34
- merges.txt +0 -0
- onnx/config.json +48 -0
- onnx/merges.txt +0 -0
- onnx/model.onnx +3 -0
- onnx/ort_config.json +35 -0
- onnx/special_tokens_map.json +30 -0
- onnx/tokenizer.json +0 -0
- onnx/tokenizer_config.json +33 -0
- onnx/vocab.json +0 -0
- special_tokens_map.json +30 -0
- tokenizer_config.json +20 -2
- vocab.json +0 -0
config.json
CHANGED
|
@@ -7,71 +7,39 @@
|
|
| 7 |
"model_type": "clip",
|
| 8 |
"projection_dim": 512,
|
| 9 |
"text_config": {
|
| 10 |
-
"add_cross_attention": false,
|
| 11 |
"attention_dropout": 0.0,
|
| 12 |
"bos_token_id": 0,
|
| 13 |
-
"cross_attention_hidden_size": null,
|
| 14 |
-
"decoder_start_token_id": null,
|
| 15 |
"dropout": 0.0,
|
| 16 |
"eos_token_id": 2,
|
| 17 |
-
"finetuning_task": null,
|
| 18 |
"hidden_act": "quick_gelu",
|
| 19 |
"hidden_size": 512,
|
| 20 |
"initializer_factor": 1.0,
|
| 21 |
"initializer_range": 0.02,
|
| 22 |
"intermediate_size": 2048,
|
| 23 |
-
"is_decoder": false,
|
| 24 |
"layer_norm_eps": 1e-05,
|
| 25 |
"max_position_embeddings": 77,
|
| 26 |
"model_type": "clip_text_model",
|
| 27 |
"num_attention_heads": 8,
|
| 28 |
"num_hidden_layers": 12,
|
| 29 |
-
"pad_token_id": 1,
|
| 30 |
-
"prefix": null,
|
| 31 |
"projection_dim": 512,
|
| 32 |
-
"pruned_heads": {},
|
| 33 |
-
"sep_token_id": null,
|
| 34 |
-
"task_specific_params": null,
|
| 35 |
-
"tie_encoder_decoder": false,
|
| 36 |
-
"tie_word_embeddings": true,
|
| 37 |
-
"tokenizer_class": null,
|
| 38 |
-
"torchscript": false,
|
| 39 |
-
"use_bfloat16": false,
|
| 40 |
"vocab_size": 49408
|
| 41 |
},
|
| 42 |
-
"transformers_version": "
|
| 43 |
"vision_config": {
|
| 44 |
-
"add_cross_attention": false,
|
| 45 |
"attention_dropout": 0.0,
|
| 46 |
-
"bos_token_id": null,
|
| 47 |
-
"cross_attention_hidden_size": null,
|
| 48 |
-
"decoder_start_token_id": null,
|
| 49 |
"dropout": 0.0,
|
| 50 |
-
"eos_token_id": null,
|
| 51 |
-
"finetuning_task": null,
|
| 52 |
"hidden_act": "quick_gelu",
|
| 53 |
"hidden_size": 768,
|
| 54 |
"image_size": 224,
|
| 55 |
"initializer_factor": 1.0,
|
| 56 |
"initializer_range": 0.02,
|
| 57 |
"intermediate_size": 3072,
|
| 58 |
-
"is_decoder": false,
|
| 59 |
"layer_norm_eps": 1e-05,
|
| 60 |
"model_type": "clip_vision_model",
|
| 61 |
"num_attention_heads": 12,
|
| 62 |
"num_channels": 3,
|
| 63 |
"num_hidden_layers": 12,
|
| 64 |
-
"pad_token_id": null,
|
| 65 |
"patch_size": 32,
|
| 66 |
-
"
|
| 67 |
-
"projection_dim": 512,
|
| 68 |
-
"pruned_heads": {},
|
| 69 |
-
"sep_token_id": null,
|
| 70 |
-
"task_specific_params": null,
|
| 71 |
-
"tie_encoder_decoder": false,
|
| 72 |
-
"tie_word_embeddings": true,
|
| 73 |
-
"tokenizer_class": null,
|
| 74 |
-
"torchscript": false,
|
| 75 |
-
"use_bfloat16": false
|
| 76 |
}
|
| 77 |
}
|
|
|
|
| 7 |
"model_type": "clip",
|
| 8 |
"projection_dim": 512,
|
| 9 |
"text_config": {
|
|
|
|
| 10 |
"attention_dropout": 0.0,
|
| 11 |
"bos_token_id": 0,
|
|
|
|
|
|
|
| 12 |
"dropout": 0.0,
|
| 13 |
"eos_token_id": 2,
|
|
|
|
| 14 |
"hidden_act": "quick_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": 77,
|
| 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": "4.57.6",
|
| 28 |
"vision_config": {
|
|
|
|
| 29 |
"attention_dropout": 0.0,
|
|
|
|
|
|
|
|
|
|
| 30 |
"dropout": 0.0,
|
|
|
|
|
|
|
| 31 |
"hidden_act": "quick_gelu",
|
| 32 |
"hidden_size": 768,
|
| 33 |
"image_size": 224,
|
| 34 |
"initializer_factor": 1.0,
|
| 35 |
"initializer_range": 0.02,
|
| 36 |
"intermediate_size": 3072,
|
|
|
|
| 37 |
"layer_norm_eps": 1e-05,
|
| 38 |
"model_type": "clip_vision_model",
|
| 39 |
"num_attention_heads": 12,
|
| 40 |
"num_channels": 3,
|
| 41 |
"num_hidden_layers": 12,
|
|
|
|
| 42 |
"patch_size": 32,
|
| 43 |
+
"projection_dim": 512
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
}
|
| 45 |
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
onnx/config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"bos_token_id": 0,
|
| 13 |
+
"dropout": 0.0,
|
| 14 |
+
"dtype": "float32",
|
| 15 |
+
"eos_token_id": 2,
|
| 16 |
+
"hidden_act": "quick_gelu",
|
| 17 |
+
"hidden_size": 512,
|
| 18 |
+
"initializer_factor": 1.0,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 2048,
|
| 21 |
+
"layer_norm_eps": 1e-05,
|
| 22 |
+
"max_position_embeddings": 77,
|
| 23 |
+
"model_type": "clip_text_model",
|
| 24 |
+
"num_attention_heads": 8,
|
| 25 |
+
"num_hidden_layers": 12,
|
| 26 |
+
"projection_dim": 512,
|
| 27 |
+
"vocab_size": 49408
|
| 28 |
+
},
|
| 29 |
+
"transformers_version": "4.57.6",
|
| 30 |
+
"vision_config": {
|
| 31 |
+
"attention_dropout": 0.0,
|
| 32 |
+
"dropout": 0.0,
|
| 33 |
+
"dtype": "float32",
|
| 34 |
+
"hidden_act": "quick_gelu",
|
| 35 |
+
"hidden_size": 768,
|
| 36 |
+
"image_size": 224,
|
| 37 |
+
"initializer_factor": 1.0,
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"intermediate_size": 3072,
|
| 40 |
+
"layer_norm_eps": 1e-05,
|
| 41 |
+
"model_type": "clip_vision_model",
|
| 42 |
+
"num_attention_heads": 12,
|
| 43 |
+
"num_channels": 3,
|
| 44 |
+
"num_hidden_layers": 12,
|
| 45 |
+
"patch_size": 32,
|
| 46 |
+
"projection_dim": 512
|
| 47 |
+
}
|
| 48 |
+
}
|
onnx/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
onnx/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1dda8a09a6f6e4d7ff4de96eb01521bb3fbc0bfc49871a35f136c67379070b5
|
| 3 |
+
size 604656405
|
onnx/ort_config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"one_external_file": true,
|
| 3 |
+
"opset": null,
|
| 4 |
+
"optimization": {
|
| 5 |
+
"disable_attention_fusion": false,
|
| 6 |
+
"disable_bias_add_fusion": false,
|
| 7 |
+
"disable_bias_gelu_fusion": false,
|
| 8 |
+
"disable_bias_skip_layer_norm_fusion": false,
|
| 9 |
+
"disable_bias_splitgelu_fusion": false,
|
| 10 |
+
"disable_embed_layer_norm_fusion": true,
|
| 11 |
+
"disable_gelu_fusion": false,
|
| 12 |
+
"disable_group_norm_fusion": true,
|
| 13 |
+
"disable_layer_norm_fusion": false,
|
| 14 |
+
"disable_nhwc_conv": false,
|
| 15 |
+
"disable_packed_kv": true,
|
| 16 |
+
"disable_packed_qkv": false,
|
| 17 |
+
"disable_rotary_embeddings": false,
|
| 18 |
+
"disable_shape_inference": true,
|
| 19 |
+
"disable_skip_group_norm_fusion": false,
|
| 20 |
+
"disable_skip_layer_norm_fusion": false,
|
| 21 |
+
"enable_gelu_approximation": false,
|
| 22 |
+
"enable_gemm_fast_gelu_fusion": false,
|
| 23 |
+
"enable_transformers_specific_optimizations": true,
|
| 24 |
+
"fp16": false,
|
| 25 |
+
"no_attention_mask": false,
|
| 26 |
+
"optimization_level": 2,
|
| 27 |
+
"optimize_for_gpu": false,
|
| 28 |
+
"use_group_norm_channels_first": false,
|
| 29 |
+
"use_mask_index": false,
|
| 30 |
+
"use_multi_head_attention": false,
|
| 31 |
+
"use_raw_attention_mask": false
|
| 32 |
+
},
|
| 33 |
+
"quantization": {},
|
| 34 |
+
"use_external_data_format": false
|
| 35 |
+
}
|
onnx/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 |
+
}
|
onnx/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
onnx/tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"backend": "tokenizers",
|
| 22 |
+
"bos_token": "<|startoftext|>",
|
| 23 |
+
"clean_up_tokenization_spaces": false,
|
| 24 |
+
"do_lower_case": true,
|
| 25 |
+
"eos_token": "<|endoftext|>",
|
| 26 |
+
"errors": "replace",
|
| 27 |
+
"extra_special_tokens": {},
|
| 28 |
+
"is_local": false,
|
| 29 |
+
"model_max_length": 77,
|
| 30 |
+
"pad_token": "<|endoftext|>",
|
| 31 |
+
"tokenizer_class": "CLIPTokenizer",
|
| 32 |
+
"unk_token": "<|endoftext|>"
|
| 33 |
+
}
|
onnx/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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_config.json
CHANGED
|
@@ -1,11 +1,29 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"bos_token": "<|startoftext|>",
|
|
|
|
| 5 |
"do_lower_case": true,
|
| 6 |
"eos_token": "<|endoftext|>",
|
| 7 |
"errors": "replace",
|
| 8 |
-
"
|
| 9 |
"model_max_length": 77,
|
| 10 |
"pad_token": "<|endoftext|>",
|
| 11 |
"tokenizer_class": "CLIPTokenizer",
|
|
|
|
| 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": 77,
|
| 28 |
"pad_token": "<|endoftext|>",
|
| 29 |
"tokenizer_class": "CLIPTokenizer",
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|