Hugging Face's logo

jingjietan
/
imgcap-soli

Image-to-Text
Transformers
PyTorch
English
vision-encoder-decoder
image-text-to-text
code
Inference Endpoints
Model card Files Community
jingjietan commited on
Commit
7085128
·
1 Parent(s): 09c3fd9

Initial commit

Browse files
Files changed (10) hide show
  1. config.json +189 -0
  2. generation_config.json +8 -0
  3. merges.txt +0 -0
  4. model.ipynb +150 -0
  5. model.pth +3 -0
  6. preprocessor_config.json +23 -0
  7. pytorch_model.bin +3 -0
  8. special_tokens_map.json +23 -0
  9. tokenizer_config.json +33 -0
  10. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "dc68f91c06a1ba6f15268e5b9c13ae7a7c514084",
3
+ "_name_or_path": "nlpconnect/vit-gpt2-image-captioning",
4
+ "architectures": [
5
+ "VisionEncoderDecoderModel"
6
+ ],
7
+ "bos_token_id": 50256,
8
+ "decoder": {
9
+ "_name_or_path": "",
10
+ "activation_function": "gelu_new",
11
+ "add_cross_attention": true,
12
+ "architectures": [
13
+ "GPT2LMHeadModel"
14
+ ],
15
+ "attn_pdrop": 0.1,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 50256,
19
+ "chunk_size_feed_forward": 0,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": 50256,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "early_stopping": false,
25
+ "embd_pdrop": 0.1,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": 50256,
28
+ "exponential_decay_length_penalty": null,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": null,
31
+ "forced_eos_token_id": null,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "is_decoder": true,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1
42
+ },
43
+ "layer_norm_epsilon": 1e-05,
44
+ "length_penalty": 1.0,
45
+ "max_length": 20,
46
+ "min_length": 0,
47
+ "model_type": "gpt2",
48
+ "n_ctx": 1024,
49
+ "n_embd": 768,
50
+ "n_head": 12,
51
+ "n_inner": null,
52
+ "n_layer": 12,
53
+ "n_positions": 1024,
54
+ "no_repeat_ngram_size": 0,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_return_sequences": 1,
58
+ "output_attentions": false,
59
+ "output_hidden_states": false,
60
+ "output_scores": false,
61
+ "pad_token_id": 50256,
62
+ "prefix": null,
63
+ "problem_type": null,
64
+ "pruned_heads": {},
65
+ "remove_invalid_values": false,
66
+ "reorder_and_upcast_attn": false,
67
+ "repetition_penalty": 1.0,
68
+ "resid_pdrop": 0.1,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "scale_attn_by_inverse_layer_idx": false,
72
+ "scale_attn_weights": true,
73
+ "sep_token_id": null,
74
+ "summary_activation": null,
75
+ "summary_first_dropout": 0.1,
76
+ "summary_proj_to_labels": true,
77
+ "summary_type": "cls_index",
78
+ "summary_use_proj": true,
79
+ "suppress_tokens": null,
80
+ "task_specific_params": {
81
+ "text-generation": {
82
+ "do_sample": true,
83
+ "max_length": 50
84
+ }
85
+ },
86
+ "temperature": 1.0,
87
+ "tf_legacy_loss": false,
88
+ "tie_encoder_decoder": false,
89
+ "tie_word_embeddings": true,
90
+ "tokenizer_class": null,
91
+ "top_k": 50,
92
+ "top_p": 1.0,
93
+ "torch_dtype": null,
94
+ "torchscript": false,
95
+ "transformers_version": "4.31.0",
96
+ "typical_p": 1.0,
97
+ "use_bfloat16": false,
98
+ "use_cache": true,
99
+ "vocab_size": 50257
100
+ },
101
+ "decoder_start_token_id": 50256,
102
+ "encoder": {
103
+ "_name_or_path": "",
104
+ "add_cross_attention": false,
105
+ "architectures": [
106
+ "ViTModel"
107
+ ],
108
+ "attention_probs_dropout_prob": 0.0,
109
+ "bad_words_ids": null,
110
+ "begin_suppress_tokens": null,
111
+ "bos_token_id": null,
112
+ "chunk_size_feed_forward": 0,
113
+ "cross_attention_hidden_size": null,
114
+ "decoder_start_token_id": null,
115
+ "diversity_penalty": 0.0,
116
+ "do_sample": false,
117
+ "early_stopping": false,
118
+ "encoder_no_repeat_ngram_size": 0,
119
+ "encoder_stride": 16,
120
+ "eos_token_id": null,
121
+ "exponential_decay_length_penalty": null,
122
+ "finetuning_task": null,
123
+ "forced_bos_token_id": null,
124
+ "forced_eos_token_id": null,
125
+ "hidden_act": "gelu",
126
+ "hidden_dropout_prob": 0.0,
127
+ "hidden_size": 768,
128
+ "id2label": {
129
+ "0": "LABEL_0",
130
+ "1": "LABEL_1"
131
+ },
132
+ "image_size": 224,
133
+ "initializer_range": 0.02,
134
+ "intermediate_size": 3072,
135
+ "is_decoder": false,
136
+ "is_encoder_decoder": false,
137
+ "label2id": {
138
+ "LABEL_0": 0,
139
+ "LABEL_1": 1
140
+ },
141
+ "layer_norm_eps": 1e-12,
142
+ "length_penalty": 1.0,
143
+ "max_length": 20,
144
+ "min_length": 0,
145
+ "model_type": "vit",
146
+ "no_repeat_ngram_size": 0,
147
+ "num_attention_heads": 12,
148
+ "num_beam_groups": 1,
149
+ "num_beams": 1,
150
+ "num_channels": 3,
151
+ "num_hidden_layers": 12,
152
+ "num_return_sequences": 1,
153
+ "output_attentions": false,
154
+ "output_hidden_states": false,
155
+ "output_scores": false,
156
+ "pad_token_id": null,
157
+ "patch_size": 16,
158
+ "prefix": null,
159
+ "problem_type": null,
160
+ "pruned_heads": {},
161
+ "qkv_bias": true,
162
+ "remove_invalid_values": false,
163
+ "repetition_penalty": 1.0,
164
+ "return_dict": true,
165
+ "return_dict_in_generate": false,
166
+ "sep_token_id": null,
167
+ "suppress_tokens": null,
168
+ "task_specific_params": null,
169
+ "temperature": 1.0,
170
+ "tf_legacy_loss": false,
171
+ "tie_encoder_decoder": false,
172
+ "tie_word_embeddings": true,
173
+ "tokenizer_class": null,
174
+ "top_k": 50,
175
+ "top_p": 1.0,
176
+ "torch_dtype": null,
177
+ "torchscript": false,
178
+ "transformers_version": "4.31.0",
179
+ "typical_p": 1.0,
180
+ "use_bfloat16": false
181
+ },
182
+ "eos_token_id": 50256,
183
+ "is_encoder_decoder": true,
184
+ "model_type": "vision-encoder-decoder",
185
+ "pad_token_id": 50256,
186
+ "tie_word_embeddings": false,
187
+ "torch_dtype": "float32",
188
+ "transformers_version": null
189
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "decoder_start_token_id": 50256,
5
+ "eos_token_id": 50256,
6
+ "pad_token_id": 50256,
7
+ "transformers_version": "4.31.0"
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.ipynb ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": 34,
6
+ "metadata": {},
7
+ "outputs": [
8
+ {
9
+ "name": "stderr",
10
+ "output_type": "stream",
11
+ "text": [
12
+ "/Users/jingjietan/Library/Python/3.9/lib/python/site-packages/huggingface_hub/file_download.py:1150: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
13
+ " warnings.warn(\n"
14
+ ]
15
+ },
16
+ {
17
+ "ename": "OSError",
18
+ "evalue": "jingjietan/imgcap-soli does not appear to have a file named config.json. Checkout 'https://huggingface.co/jingjietan/imgcap-soli/main' for available files.",
19
+ "output_type": "error",
20
+ "traceback": [
21
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
22
+ "\u001b[0;31mHTTPError\u001b[0m Traceback (most recent call last)",
23
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/huggingface_hub/utils/_errors.py:304\u001b[0m, in \u001b[0;36mhf_raise_for_status\u001b[0;34m(response, endpoint_name)\u001b[0m\n\u001b[1;32m 303\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 304\u001b[0m \u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mraise_for_status\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 305\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m HTTPError \u001b[38;5;28;01mas\u001b[39;00m e:\n",
24
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/requests/models.py:1024\u001b[0m, in \u001b[0;36mResponse.raise_for_status\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1023\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m http_error_msg:\n\u001b[0;32m-> 1024\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m HTTPError(http_error_msg, response\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m)\n",
25
+ "\u001b[0;31mHTTPError\u001b[0m: 404 Client Error: Not Found for url: https://huggingface.co/jingjietan/imgcap-soli/resolve/main/config.json",
26
+ "\nThe above exception was the direct cause of the following exception:\n",
27
+ "\u001b[0;31mEntryNotFoundError\u001b[0m Traceback (most recent call last)",
28
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/transformers/utils/hub.py:417\u001b[0m, in \u001b[0;36mcached_file\u001b[0;34m(path_or_repo_id, filename, cache_dir, force_download, resume_download, proxies, use_auth_token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash)\u001b[0m\n\u001b[1;32m 415\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 416\u001b[0m \u001b[38;5;66;03m# Load from URL or cache if already cached\u001b[39;00m\n\u001b[0;32m--> 417\u001b[0m resolved_file \u001b[38;5;241m=\u001b[39m \u001b[43mhf_hub_download\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 418\u001b[0m \u001b[43m \u001b[49m\u001b[43mpath_or_repo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 419\u001b[0m \u001b[43m \u001b[49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 420\u001b[0m \u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43msubfolder\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m==\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 421\u001b[0m \u001b[43m \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 422\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 423\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 424\u001b[0m \u001b[43m \u001b[49m\u001b[43muser_agent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muser_agent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 425\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 426\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 427\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 428\u001b[0m \u001b[43m \u001b[49m\u001b[43muse_auth_token\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_auth_token\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 429\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 430\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 432\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m RepositoryNotFoundError:\n",
29
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/huggingface_hub/utils/_deprecation.py:101\u001b[0m, in \u001b[0;36m_deprecate_arguments.<locals>._inner_deprecate_positional_args.<locals>.inner_f\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 100\u001b[0m warnings\u001b[38;5;241m.\u001b[39mwarn(message, \u001b[38;5;167;01mFutureWarning\u001b[39;00m)\n\u001b[0;32m--> 101\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
30
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/huggingface_hub/utils/_validators.py:114\u001b[0m, in \u001b[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 112\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m smoothly_deprecate_use_auth_token(fn_name\u001b[38;5;241m=\u001b[39mfn\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, has_token\u001b[38;5;241m=\u001b[39mhas_token, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[0;32m--> 114\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
31
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/huggingface_hub/file_download.py:1240\u001b[0m, in \u001b[0;36mhf_hub_download\u001b[0;34m(repo_id, filename, subfolder, repo_type, revision, library_name, library_version, cache_dir, local_dir, user_agent, force_download, proxies, etag_timeout, token, local_files_only, headers, endpoint, legacy_cache_layout, resume_download, force_filename, local_dir_use_symlinks)\u001b[0m\n\u001b[1;32m 1239\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1240\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_hf_hub_download_to_cache_dir\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1241\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# Destination\u001b[39;49;00m\n\u001b[1;32m 1242\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1243\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# File info\u001b[39;49;00m\n\u001b[1;32m 1244\u001b[0m \u001b[43m \u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1245\u001b[0m \u001b[43m \u001b[49m\u001b[43mfilename\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1246\u001b[0m \u001b[43m \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1247\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1248\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# HTTP info\u001b[39;49;00m\n\u001b[1;32m 1249\u001b[0m \u001b[43m \u001b[49m\u001b[43mendpoint\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mendpoint\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1250\u001b[0m \u001b[43m \u001b[49m\u001b[43metag_timeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43metag_timeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1251\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1252\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1253\u001b[0m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1254\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;66;43;03m# Additional options\u001b[39;49;00m\n\u001b[1;32m 1255\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1256\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1257\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
32
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/huggingface_hub/file_download.py:1303\u001b[0m, in \u001b[0;36m_hf_hub_download_to_cache_dir\u001b[0;34m(cache_dir, repo_id, filename, repo_type, revision, endpoint, etag_timeout, headers, proxies, token, local_files_only, force_download)\u001b[0m\n\u001b[1;32m 1301\u001b[0m \u001b[38;5;66;03m# Try to get metadata (etag, commit_hash, url, size) from the server.\u001b[39;00m\n\u001b[1;32m 1302\u001b[0m \u001b[38;5;66;03m# If we can't, a HEAD request error is returned.\u001b[39;00m\n\u001b[0;32m-> 1303\u001b[0m (url_to_download, etag, commit_hash, expected_size, head_call_error) \u001b[38;5;241m=\u001b[39m \u001b[43m_get_metadata_or_catch_error\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1304\u001b[0m \u001b[43m \u001b[49m\u001b[43mrepo_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1305\u001b[0m \u001b[43m \u001b[49m\u001b[43mfilename\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1306\u001b[0m \u001b[43m \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1307\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1308\u001b[0m \u001b[43m \u001b[49m\u001b[43mendpoint\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mendpoint\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1309\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1310\u001b[0m \u001b[43m \u001b[49m\u001b[43metag_timeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43metag_timeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1311\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1312\u001b[0m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1313\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1314\u001b[0m \u001b[43m \u001b[49m\u001b[43mstorage_folder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstorage_folder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1315\u001b[0m \u001b[43m \u001b[49m\u001b[43mrelative_filename\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrelative_filename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1316\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1318\u001b[0m \u001b[38;5;66;03m# etag can be None for several reasons:\u001b[39;00m\n\u001b[1;32m 1319\u001b[0m \u001b[38;5;66;03m# 1. we passed local_files_only.\u001b[39;00m\n\u001b[1;32m 1320\u001b[0m \u001b[38;5;66;03m# 2. we don't have a connection\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1326\u001b[0m \u001b[38;5;66;03m# If the specified revision is a commit hash, look inside \"snapshots\".\u001b[39;00m\n\u001b[1;32m 1327\u001b[0m \u001b[38;5;66;03m# If the specified revision is a branch or tag, look inside \"refs\".\u001b[39;00m\n",
33
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/huggingface_hub/file_download.py:1751\u001b[0m, in \u001b[0;36m_get_metadata_or_catch_error\u001b[0;34m(repo_id, filename, repo_type, revision, endpoint, proxies, etag_timeout, headers, token, local_files_only, relative_filename, storage_folder)\u001b[0m\n\u001b[1;32m 1750\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1751\u001b[0m metadata \u001b[38;5;241m=\u001b[39m \u001b[43mget_hf_file_metadata\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1752\u001b[0m \u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43metag_timeout\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\n\u001b[1;32m 1753\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1754\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m EntryNotFoundError \u001b[38;5;28;01mas\u001b[39;00m http_error:\n",
34
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/huggingface_hub/utils/_validators.py:114\u001b[0m, in \u001b[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 112\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m smoothly_deprecate_use_auth_token(fn_name\u001b[38;5;241m=\u001b[39mfn\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, has_token\u001b[38;5;241m=\u001b[39mhas_token, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[0;32m--> 114\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
35
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/huggingface_hub/file_download.py:1673\u001b[0m, in \u001b[0;36mget_hf_file_metadata\u001b[0;34m(url, token, proxies, timeout, library_name, library_version, user_agent, headers)\u001b[0m\n\u001b[1;32m 1672\u001b[0m \u001b[38;5;66;03m# Retrieve metadata\u001b[39;00m\n\u001b[0;32m-> 1673\u001b[0m r \u001b[38;5;241m=\u001b[39m \u001b[43m_request_wrapper\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1674\u001b[0m \u001b[43m \u001b[49m\u001b[43mmethod\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mHEAD\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1675\u001b[0m \u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1676\u001b[0m \u001b[43m \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1677\u001b[0m \u001b[43m \u001b[49m\u001b[43mallow_redirects\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 1678\u001b[0m \u001b[43m \u001b[49m\u001b[43mfollow_relative_redirects\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 1679\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1680\u001b[0m \u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1681\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1682\u001b[0m hf_raise_for_status(r)\n",
36
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/huggingface_hub/file_download.py:376\u001b[0m, in \u001b[0;36m_request_wrapper\u001b[0;34m(method, url, follow_relative_redirects, **params)\u001b[0m\n\u001b[1;32m 375\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m follow_relative_redirects:\n\u001b[0;32m--> 376\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43m_request_wrapper\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 377\u001b[0m \u001b[43m \u001b[49m\u001b[43mmethod\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 378\u001b[0m \u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 379\u001b[0m \u001b[43m \u001b[49m\u001b[43mfollow_relative_redirects\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 380\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mparams\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 381\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 383\u001b[0m \u001b[38;5;66;03m# If redirection, we redirect only relative paths.\u001b[39;00m\n\u001b[1;32m 384\u001b[0m \u001b[38;5;66;03m# This is useful in case of a renamed repository.\u001b[39;00m\n",
37
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/huggingface_hub/file_download.py:400\u001b[0m, in \u001b[0;36m_request_wrapper\u001b[0;34m(method, url, follow_relative_redirects, **params)\u001b[0m\n\u001b[1;32m 399\u001b[0m response \u001b[38;5;241m=\u001b[39m get_session()\u001b[38;5;241m.\u001b[39mrequest(method\u001b[38;5;241m=\u001b[39mmethod, url\u001b[38;5;241m=\u001b[39murl, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mparams)\n\u001b[0;32m--> 400\u001b[0m \u001b[43mhf_raise_for_status\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresponse\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 401\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m response\n",
38
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/huggingface_hub/utils/_errors.py:315\u001b[0m, in \u001b[0;36mhf_raise_for_status\u001b[0;34m(response, endpoint_name)\u001b[0m\n\u001b[1;32m 314\u001b[0m message \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mresponse\u001b[38;5;241m.\u001b[39mstatus_code\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m Client Error.\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mEntry Not Found for url: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mresponse\u001b[38;5;241m.\u001b[39murl\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m--> 315\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m EntryNotFoundError(message, response) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[1;32m 317\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m error_code \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mGatedRepo\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n",
39
+ "\u001b[0;31mEntryNotFoundError\u001b[0m: 404 Client Error. (Request ID: Root=1-66a06487-6c5463b77a6ce8ac179471d5;3c844433-84a2-4e5d-80c8-ac690b161502)\n\nEntry Not Found for url: https://huggingface.co/jingjietan/imgcap-soli/resolve/main/config.json.",
40
+ "\nDuring handling of the above exception, another exception occurred:\n",
41
+ "\u001b[0;31mOSError\u001b[0m Traceback (most recent call last)",
42
+ "Cell \u001b[0;32mIn[34], line 4\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# Load model directly\u001b[39;00m\n\u001b[1;32m 2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m VisionEncoderDecoderModel, ViTFeatureExtractor, GPT2Tokenizer\n\u001b[0;32m----> 4\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[43mVisionEncoderDecoderModel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mjingjietan/imgcap-soli\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 5\u001b[0m feature_extractor \u001b[38;5;241m=\u001b[39m ViTFeatureExtractor\u001b[38;5;241m.\u001b[39mfrom_pretrained(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mjingjietan/imgcap-soli\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 6\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m GPT2Tokenizer\u001b[38;5;241m.\u001b[39mfrom_pretrained(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mgpt2\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
43
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/transformers/models/vision_encoder_decoder/modeling_vision_encoder_decoder.py:363\u001b[0m, in \u001b[0;36mVisionEncoderDecoderModel.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, *model_args, **kwargs)\u001b[0m\n\u001b[1;32m 357\u001b[0m logger\u001b[38;5;241m.\u001b[39mwarning(\n\u001b[1;32m 358\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFast initialization is currently not supported for VisionEncoderDecoderModel. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 359\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFalling back to slow initialization...\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 360\u001b[0m )\n\u001b[1;32m 361\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_fast_init\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[0;32m--> 363\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmodel_args\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
44
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/transformers/modeling_utils.py:2325\u001b[0m, in \u001b[0;36mPreTrainedModel.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, *model_args, **kwargs)\u001b[0m\n\u001b[1;32m 2323\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(config, PretrainedConfig):\n\u001b[1;32m 2324\u001b[0m config_path \u001b[38;5;241m=\u001b[39m config \u001b[38;5;28;01mif\u001b[39;00m config \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m pretrained_model_name_or_path\n\u001b[0;32m-> 2325\u001b[0m config, model_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mconfig_class\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 2326\u001b[0m \u001b[43m \u001b[49m\u001b[43mconfig_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2327\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2328\u001b[0m \u001b[43m \u001b[49m\u001b[43mreturn_unused_kwargs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 2329\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2330\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2331\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2332\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2333\u001b[0m \u001b[43m \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2334\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2335\u001b[0m \u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msubfolder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2336\u001b[0m \u001b[43m \u001b[49m\u001b[43m_from_auto\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfrom_auto_class\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2337\u001b[0m \u001b[43m \u001b[49m\u001b[43m_from_pipeline\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfrom_pipeline\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2338\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2339\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2340\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 2341\u001b[0m model_kwargs \u001b[38;5;241m=\u001b[39m kwargs\n",
45
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/transformers/configuration_utils.py:590\u001b[0m, in \u001b[0;36mPretrainedConfig.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, cache_dir, force_download, local_files_only, token, revision, **kwargs)\u001b[0m\n\u001b[1;32m 586\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrevision\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m revision\n\u001b[1;32m 588\u001b[0m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_set_token_in_kwargs(kwargs, token)\n\u001b[0;32m--> 590\u001b[0m config_dict, kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_config_dict\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 591\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel_type\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m config_dict \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(\u001b[38;5;28mcls\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel_type\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;129;01mand\u001b[39;00m config_dict[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel_type\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m!=\u001b[39m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39mmodel_type:\n\u001b[1;32m 592\u001b[0m logger\u001b[38;5;241m.\u001b[39mwarning(\n\u001b[1;32m 593\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mYou are using a model of type \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mconfig_dict[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mmodel_type\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m to instantiate a model of type \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 594\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39mmodel_type\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m. This is not supported for all configurations of models and can yield errors.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 595\u001b[0m )\n",
46
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/transformers/configuration_utils.py:617\u001b[0m, in \u001b[0;36mPretrainedConfig.get_config_dict\u001b[0;34m(cls, pretrained_model_name_or_path, **kwargs)\u001b[0m\n\u001b[1;32m 615\u001b[0m original_kwargs \u001b[38;5;241m=\u001b[39m copy\u001b[38;5;241m.\u001b[39mdeepcopy(kwargs)\n\u001b[1;32m 616\u001b[0m \u001b[38;5;66;03m# Get config dict associated with the base config file\u001b[39;00m\n\u001b[0;32m--> 617\u001b[0m config_dict, kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_config_dict\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 618\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_commit_hash\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m config_dict:\n\u001b[1;32m 619\u001b[0m original_kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_commit_hash\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m config_dict[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_commit_hash\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n",
47
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/transformers/configuration_utils.py:672\u001b[0m, in \u001b[0;36mPretrainedConfig._get_config_dict\u001b[0;34m(cls, pretrained_model_name_or_path, **kwargs)\u001b[0m\n\u001b[1;32m 668\u001b[0m configuration_file \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_configuration_file\u001b[39m\u001b[38;5;124m\"\u001b[39m, CONFIG_NAME)\n\u001b[1;32m 670\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 671\u001b[0m \u001b[38;5;66;03m# Load from local folder or from cache or download from model Hub and cache\u001b[39;00m\n\u001b[0;32m--> 672\u001b[0m resolved_config_file \u001b[38;5;241m=\u001b[39m \u001b[43mcached_file\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 673\u001b[0m \u001b[43m \u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 674\u001b[0m \u001b[43m \u001b[49m\u001b[43mconfiguration_file\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 675\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 676\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 677\u001b[0m \u001b[43m \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 678\u001b[0m \u001b[43m \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 679\u001b[0m \u001b[43m \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 680\u001b[0m \u001b[43m \u001b[49m\u001b[43muse_auth_token\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_auth_token\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 681\u001b[0m \u001b[43m \u001b[49m\u001b[43muser_agent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muser_agent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 682\u001b[0m \u001b[43m \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 683\u001b[0m \u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msubfolder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 684\u001b[0m \u001b[43m \u001b[49m\u001b[43m_commit_hash\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcommit_hash\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 685\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 686\u001b[0m commit_hash \u001b[38;5;241m=\u001b[39m extract_commit_hash(resolved_config_file, commit_hash)\n\u001b[1;32m 687\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m:\n\u001b[1;32m 688\u001b[0m \u001b[38;5;66;03m# Raise any environment error raise by `cached_file`. It will have a helpful error message adapted to\u001b[39;00m\n\u001b[1;32m 689\u001b[0m \u001b[38;5;66;03m# the original exception.\u001b[39;00m\n",
48
+ "File \u001b[0;32m~/Library/Python/3.9/lib/python/site-packages/transformers/utils/hub.py:463\u001b[0m, in \u001b[0;36mcached_file\u001b[0;34m(path_or_repo_id, filename, cache_dir, force_download, resume_download, proxies, use_auth_token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash)\u001b[0m\n\u001b[1;32m 461\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m revision \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 462\u001b[0m revision \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmain\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m--> 463\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m(\n\u001b[1;32m 464\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpath_or_repo_id\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m does not appear to have a file named \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfull_filename\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m. Checkout \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 465\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mhttps://huggingface.co/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpath_or_repo_id\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mrevision\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m for available files.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 466\u001b[0m )\n\u001b[1;32m 467\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m HTTPError \u001b[38;5;28;01mas\u001b[39;00m err:\n\u001b[1;32m 468\u001b[0m \u001b[38;5;66;03m# First we try to see if we have a cached version (not up to date):\u001b[39;00m\n\u001b[1;32m 469\u001b[0m resolved_file \u001b[38;5;241m=\u001b[39m try_to_load_from_cache(path_or_repo_id, full_filename, cache_dir\u001b[38;5;241m=\u001b[39mcache_dir, revision\u001b[38;5;241m=\u001b[39mrevision)\n",
49
+ "\u001b[0;31mOSError\u001b[0m: jingjietan/imgcap-soli does not appear to have a file named config.json. Checkout 'https://huggingface.co/jingjietan/imgcap-soli/main' for available files."
50
+ ]
51
+ }
52
+ ],
53
+ "source": [
54
+ "# Load model directly\n",
55
+ "from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, GPT2Tokenizer\n",
56
+ "\n",
57
+ "model = VisionEncoderDecoderModel.from_pretrained(\"jingjietan/imgcap-soli\")\n",
58
+ "feature_extractor = ViTFeatureExtractor.from_pretrained(\"jingjietan/imgcap-soli\")\n",
59
+ "tokenizer = GPT2Tokenizer.from_pretrained(\"gpt2\")"
60
+ ]
61
+ },
62
+ {
63
+ "cell_type": "code",
64
+ "execution_count": 30,
65
+ "metadata": {},
66
+ "outputs": [
67
+ {
68
+ "name": "stderr",
69
+ "output_type": "stream",
70
+ "text": [
71
+ "/Users/jingjietan/Library/Python/3.9/lib/python/site-packages/transformers/generation/utils.py:1369: UserWarning: Using `max_length`'s default (20) to control the generation length. This behaviour is deprecated and will be removed from the config in v5 of Transformers -- we recommend using `max_new_tokens` to control the maximum length of the generation.\n",
72
+ " warnings.warn(\n"
73
+ ]
74
+ },
75
+ {
76
+ "name": "stdout",
77
+ "output_type": "stream",
78
+ "text": [
79
+ "a series of photos showing a patterned pattern on a blue and white checkered pattern \n"
80
+ ]
81
+ }
82
+ ],
83
+ "source": [
84
+ "\n",
85
+ "image = Image.open(\"sample.png\").convert('RGB')\n",
86
+ "\n",
87
+ "# Preprocess the image\n",
88
+ "inputs = feature_extractor(images=image, return_tensors=\"pt\")\n",
89
+ "\n",
90
+ "# Generate a caption\n",
91
+ "outputs = model.generate(pixel_values=inputs['pixel_values'])\n",
92
+ "caption = tokenizer.decode(outputs[0], skip_special_tokens=True)\n",
93
+ "\n",
94
+ "print(caption)"
95
+ ]
96
+ },
97
+ {
98
+ "cell_type": "code",
99
+ "execution_count": 33,
100
+ "metadata": {},
101
+ "outputs": [
102
+ {
103
+ "data": {
104
+ "text/plain": [
105
+ "('tokenizer/tokenizer_config.json',\n",
106
+ " 'tokenizer/special_tokens_map.json',\n",
107
+ " 'tokenizer/vocab.json',\n",
108
+ " 'tokenizer/merges.txt',\n",
109
+ " 'tokenizer/added_tokens.json')"
110
+ ]
111
+ },
112
+ "execution_count": 33,
113
+ "metadata": {},
114
+ "output_type": "execute_result"
115
+ }
116
+ ],
117
+ "source": [
118
+ "#save weight dict\n",
119
+ "import torch\n",
120
+ "torch.save(model.state_dict(), \"model.pth\")\n",
121
+ "\n",
122
+ "# save feature extractor and tokenizer\n",
123
+ "model.save_pretrained(\"model\")\n",
124
+ "feature_extractor.save_pretrained(\"feature_extractor\")\n",
125
+ "tokenizer.save_pretrained(\"tokenizer\")"
126
+ ]
127
+ }
128
+ ],
129
+ "metadata": {
130
+ "kernelspec": {
131
+ "display_name": "Python 3",
132
+ "language": "python",
133
+ "name": "python3"
134
+ },
135
+ "language_info": {
136
+ "codemirror_mode": {
137
+ "name": "ipython",
138
+ "version": 3
139
+ },
140
+ "file_extension": ".py",
141
+ "mimetype": "text/x-python",
142
+ "name": "python",
143
+ "nbconvert_exporter": "python",
144
+ "pygments_lexer": "ipython3",
145
+ "version": "3.9.6"
146
+ }
147
+ },
148
+ "nbformat": 4,
149
+ "nbformat_minor": 2
150
+ }
model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:187b1c87636b99f53ad4ee6386c414418c2397d1ad944797e836a0be86c653a7
3
+ size 956927162
preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "feature_extractor_type": "ViTFeatureExtractor",
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "ViTFeatureExtractor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "resample": 2,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ }
23
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a6a13613cfef25af5b0b0fe658dcceb2b2ba700b6599673b34e19c31bd0f6c6
3
+ size 956929466
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
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": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1024,
23
+ "pad_token": null,
24
+ "tokenizer_class": "GPT2Tokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff