Hugging Face's logo

ydshieh
/
vit-gpt2-coco-en-ckpts

Image Classification PyTorch JAX TensorBoard generic vision-encoder-decoder
Model card Files Metrics Community
3
ydshieh HF staff commited on
Commit
bd6eff2
•
1 Parent(s): 5f9dae7

remove some ckpts

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. ckpt_epoch_1_step_1200/config.json +0 -169
  2. ckpt_epoch_1_step_1200/flax_model.msgpack +0 -3
  3. ckpt_epoch_1_step_1200/generation_eval.json +0 -0
  4. ckpt_epoch_1_step_1200/merges.txt +0 -0
  5. ckpt_epoch_1_step_1200/special_tokens_map.json +0 -1
  6. ckpt_epoch_1_step_1200/tokenizer.json +0 -0
  7. ckpt_epoch_1_step_1200/tokenizer_config.json +0 -1
  8. ckpt_epoch_1_step_1200/vocab.json +0 -0
  9. ckpt_epoch_1_step_1500/config.json +0 -169
  10. ckpt_epoch_1_step_1500/flax_model.msgpack +0 -3
  11. ckpt_epoch_1_step_1500/generation_eval.json +0 -0
  12. ckpt_epoch_1_step_1500/merges.txt +0 -0
  13. ckpt_epoch_1_step_1500/special_tokens_map.json +0 -1
  14. ckpt_epoch_1_step_1500/tokenizer.json +0 -0
  15. ckpt_epoch_1_step_1500/tokenizer_config.json +0 -1
  16. ckpt_epoch_1_step_1500/vocab.json +0 -0
  17. ckpt_epoch_1_step_1800/config.json +0 -169
  18. ckpt_epoch_1_step_1800/flax_model.msgpack +0 -3
  19. ckpt_epoch_1_step_1800/generation_eval.json +0 -0
  20. ckpt_epoch_1_step_1800/merges.txt +0 -0
  21. ckpt_epoch_1_step_1800/special_tokens_map.json +0 -1
  22. ckpt_epoch_1_step_1800/tokenizer.json +0 -0
  23. ckpt_epoch_1_step_1800/tokenizer_config.json +0 -1
  24. ckpt_epoch_1_step_1800/vocab.json +0 -0
  25. ckpt_epoch_1_step_2100/config.json +0 -169
  26. ckpt_epoch_1_step_2100/flax_model.msgpack +0 -3
  27. ckpt_epoch_1_step_2100/generation_eval.json +0 -0
  28. ckpt_epoch_1_step_2100/merges.txt +0 -0
  29. ckpt_epoch_1_step_2100/special_tokens_map.json +0 -1
  30. ckpt_epoch_1_step_2100/tokenizer.json +0 -0
  31. ckpt_epoch_1_step_2100/tokenizer_config.json +0 -1
  32. ckpt_epoch_1_step_2100/vocab.json +0 -0
  33. ckpt_epoch_1_step_600/config.json +0 -169
  34. ckpt_epoch_1_step_600/flax_model.msgpack +0 -3
  35. ckpt_epoch_1_step_600/generation_eval.json +0 -0
  36. ckpt_epoch_1_step_600/merges.txt +0 -0
  37. ckpt_epoch_1_step_600/special_tokens_map.json +0 -1
  38. ckpt_epoch_1_step_600/tokenizer.json +0 -0
  39. ckpt_epoch_1_step_600/tokenizer_config.json +0 -1
  40. ckpt_epoch_1_step_600/vocab.json +0 -0
  41. ckpt_epoch_1_step_900/config.json +0 -169
  42. ckpt_epoch_1_step_900/flax_model.msgpack +0 -3
  43. ckpt_epoch_1_step_900/generation_eval.json +0 -0
  44. ckpt_epoch_1_step_900/merges.txt +0 -0
  45. ckpt_epoch_1_step_900/special_tokens_map.json +0 -1
  46. ckpt_epoch_1_step_900/tokenizer.json +0 -0
  47. ckpt_epoch_1_step_900/tokenizer_config.json +0 -1
  48. ckpt_epoch_1_step_900/vocab.json +0 -0
  49. ckpt_epoch_2_step_2400/config.json +0 -169
  50. ckpt_epoch_2_step_2400/flax_model.msgpack +0 -3
ckpt_epoch_1_step_1200/config.json DELETED
@@ -1,169 +0,0 @@
1
- {
2
- "architectures": [
3
- "VisionEncoderDecoderModel"
4
- ],
5
- "bos_token_id": 50256,
6
- "decoder": {
7
- "_name_or_path": "",
8
- "activation_function": "gelu_new",
9
- "add_cross_attention": true,
10
- "architectures": [
11
- "GPT2LMHeadModel"
12
- ],
13
- "attn_pdrop": 0.1,
14
- "bad_words_ids": null,
15
- "bos_token_id": 50256,
16
- "chunk_size_feed_forward": 0,
17
- "decoder_start_token_id": 50256,
18
- "diversity_penalty": 0.0,
19
- "do_sample": false,
20
- "early_stopping": false,
21
- "embd_pdrop": 0.1,
22
- "encoder_no_repeat_ngram_size": 0,
23
- "eos_token_id": 50256,
24
- "finetuning_task": null,
25
- "forced_bos_token_id": null,
26
- "forced_eos_token_id": null,
27
- "id2label": {
28
- "0": "LABEL_0",
29
- "1": "LABEL_1"
30
- },
31
- "initializer_range": 0.02,
32
- "is_decoder": true,
33
- "is_encoder_decoder": false,
34
- "label2id": {
35
- "LABEL_0": 0,
36
- "LABEL_1": 1
37
- },
38
- "layer_norm_epsilon": 1e-05,
39
- "length_penalty": 1.0,
40
- "max_length": 20,
41
- "min_length": 0,
42
- "model_type": "gpt2",
43
- "n_ctx": 1024,
44
- "n_embd": 768,
45
- "n_head": 12,
46
- "n_inner": null,
47
- "n_layer": 12,
48
- "n_positions": 1024,
49
- "no_repeat_ngram_size": 0,
50
- "num_beam_groups": 1,
51
- "num_beams": 1,
52
- "num_return_sequences": 1,
53
- "output_attentions": false,
54
- "output_hidden_states": false,
55
- "output_scores": false,
56
- "pad_token_id": 50256,
57
- "prefix": null,
58
- "problem_type": null,
59
- "pruned_heads": {},
60
- "remove_invalid_values": false,
61
- "repetition_penalty": 1.0,
62
- "resid_pdrop": 0.1,
63
- "return_dict": true,
64
- "return_dict_in_generate": false,
65
- "scale_attn_weights": true,
66
- "sep_token_id": null,
67
- "summary_activation": null,
68
- "summary_first_dropout": 0.1,
69
- "summary_proj_to_labels": true,
70
- "summary_type": "cls_index",
71
- "summary_use_proj": true,
72
- "task_specific_params": {
73
- "text-generation": {
74
- "do_sample": true,
75
- "max_length": 50
76
- }
77
- },
78
- "temperature": 1.0,
79
- "tie_encoder_decoder": false,
80
- "tie_word_embeddings": true,
81
- "tokenizer_class": null,
82
- "top_k": 50,
83
- "top_p": 1.0,
84
- "torch_dtype": null,
85
- "torchscript": false,
86
- "transformers_version": "4.11.0.dev0",
87
- "use_bfloat16": false,
88
- "use_cache": true,
89
- "vocab_size": 50257
90
- },
91
- "decoder_start_token_id": 50256,
92
- "encoder": {
93
- "_name_or_path": "",
94
- "add_cross_attention": false,
95
- "architectures": [
96
- "ViTModel"
97
- ],
98
- "attention_probs_dropout_prob": 0.0,
99
- "bad_words_ids": null,
100
- "bos_token_id": null,
101
- "chunk_size_feed_forward": 0,
102
- "decoder_start_token_id": null,
103
- "diversity_penalty": 0.0,
104
- "do_sample": false,
105
- "early_stopping": false,
106
- "encoder_no_repeat_ngram_size": 0,
107
- "eos_token_id": null,
108
- "finetuning_task": null,
109
- "forced_bos_token_id": null,
110
- "forced_eos_token_id": null,
111
- "hidden_act": "gelu",
112
- "hidden_dropout_prob": 0.0,
113
- "hidden_size": 768,
114
- "id2label": {
115
- "0": "LABEL_0",
116
- "1": "LABEL_1"
117
- },
118
- "image_size": 224,
119
- "initializer_range": 0.02,
120
- "intermediate_size": 3072,
121
- "is_decoder": false,
122
- "is_encoder_decoder": false,
123
- "label2id": {
124
- "LABEL_0": 0,
125
- "LABEL_1": 1
126
- },
127
- "layer_norm_eps": 1e-12,
128
- "length_penalty": 1.0,
129
- "max_length": 20,
130
- "min_length": 0,
131
- "model_type": "vit",
132
- "no_repeat_ngram_size": 0,
133
- "num_attention_heads": 12,
134
- "num_beam_groups": 1,
135
- "num_beams": 1,
136
- "num_channels": 3,
137
- "num_hidden_layers": 12,
138
- "num_return_sequences": 1,
139
- "output_attentions": false,
140
- "output_hidden_states": false,
141
- "output_scores": false,
142
- "pad_token_id": null,
143
- "patch_size": 16,
144
- "prefix": null,
145
- "problem_type": null,
146
- "pruned_heads": {},
147
- "remove_invalid_values": false,
148
- "repetition_penalty": 1.0,
149
- "return_dict": true,
150
- "return_dict_in_generate": false,
151
- "sep_token_id": null,
152
- "task_specific_params": null,
153
- "temperature": 1.0,
154
- "tie_encoder_decoder": false,
155
- "tie_word_embeddings": true,
156
- "tokenizer_class": null,
157
- "top_k": 50,
158
- "top_p": 1.0,
159
- "torch_dtype": null,
160
- "torchscript": false,
161
- "transformers_version": "4.11.0.dev0",
162
- "use_bfloat16": false
163
- },
164
- "eos_token_id": 50256,
165
- "is_encoder_decoder": true,
166
- "model_type": "vision-encoder-decoder",
167
- "pad_token_id": 50256,
168
- "transformers_version": null
169
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt_epoch_1_step_1200/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:83f68c25e86ba57002d1a5d9164ddb22c494fcd142c291c67a88d85eea637365
3
- size 956799284
 
 
 
ckpt_epoch_1_step_1200/generation_eval.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_1200/merges.txt DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_1200/special_tokens_map.json DELETED
@@ -1 +0,0 @@
1
- {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
 
ckpt_epoch_1_step_1200/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_1200/tokenizer_config.json DELETED
@@ -1 +0,0 @@
1
- {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
 
ckpt_epoch_1_step_1200/vocab.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_1500/config.json DELETED
@@ -1,169 +0,0 @@
1
- {
2
- "architectures": [
3
- "VisionEncoderDecoderModel"
4
- ],
5
- "bos_token_id": 50256,
6
- "decoder": {
7
- "_name_or_path": "",
8
- "activation_function": "gelu_new",
9
- "add_cross_attention": true,
10
- "architectures": [
11
- "GPT2LMHeadModel"
12
- ],
13
- "attn_pdrop": 0.1,
14
- "bad_words_ids": null,
15
- "bos_token_id": 50256,
16
- "chunk_size_feed_forward": 0,
17
- "decoder_start_token_id": 50256,
18
- "diversity_penalty": 0.0,
19
- "do_sample": false,
20
- "early_stopping": false,
21
- "embd_pdrop": 0.1,
22
- "encoder_no_repeat_ngram_size": 0,
23
- "eos_token_id": 50256,
24
- "finetuning_task": null,
25
- "forced_bos_token_id": null,
26
- "forced_eos_token_id": null,
27
- "id2label": {
28
- "0": "LABEL_0",
29
- "1": "LABEL_1"
30
- },
31
- "initializer_range": 0.02,
32
- "is_decoder": true,
33
- "is_encoder_decoder": false,
34
- "label2id": {
35
- "LABEL_0": 0,
36
- "LABEL_1": 1
37
- },
38
- "layer_norm_epsilon": 1e-05,
39
- "length_penalty": 1.0,
40
- "max_length": 20,
41
- "min_length": 0,
42
- "model_type": "gpt2",
43
- "n_ctx": 1024,
44
- "n_embd": 768,
45
- "n_head": 12,
46
- "n_inner": null,
47
- "n_layer": 12,
48
- "n_positions": 1024,
49
- "no_repeat_ngram_size": 0,
50
- "num_beam_groups": 1,
51
- "num_beams": 1,
52
- "num_return_sequences": 1,
53
- "output_attentions": false,
54
- "output_hidden_states": false,
55
- "output_scores": false,
56
- "pad_token_id": 50256,
57
- "prefix": null,
58
- "problem_type": null,
59
- "pruned_heads": {},
60
- "remove_invalid_values": false,
61
- "repetition_penalty": 1.0,
62
- "resid_pdrop": 0.1,
63
- "return_dict": true,
64
- "return_dict_in_generate": false,
65
- "scale_attn_weights": true,
66
- "sep_token_id": null,
67
- "summary_activation": null,
68
- "summary_first_dropout": 0.1,
69
- "summary_proj_to_labels": true,
70
- "summary_type": "cls_index",
71
- "summary_use_proj": true,
72
- "task_specific_params": {
73
- "text-generation": {
74
- "do_sample": true,
75
- "max_length": 50
76
- }
77
- },
78
- "temperature": 1.0,
79
- "tie_encoder_decoder": false,
80
- "tie_word_embeddings": true,
81
- "tokenizer_class": null,
82
- "top_k": 50,
83
- "top_p": 1.0,
84
- "torch_dtype": null,
85
- "torchscript": false,
86
- "transformers_version": "4.11.0.dev0",
87
- "use_bfloat16": false,
88
- "use_cache": true,
89
- "vocab_size": 50257
90
- },
91
- "decoder_start_token_id": 50256,
92
- "encoder": {
93
- "_name_or_path": "",
94
- "add_cross_attention": false,
95
- "architectures": [
96
- "ViTModel"
97
- ],
98
- "attention_probs_dropout_prob": 0.0,
99
- "bad_words_ids": null,
100
- "bos_token_id": null,
101
- "chunk_size_feed_forward": 0,
102
- "decoder_start_token_id": null,
103
- "diversity_penalty": 0.0,
104
- "do_sample": false,
105
- "early_stopping": false,
106
- "encoder_no_repeat_ngram_size": 0,
107
- "eos_token_id": null,
108
- "finetuning_task": null,
109
- "forced_bos_token_id": null,
110
- "forced_eos_token_id": null,
111
- "hidden_act": "gelu",
112
- "hidden_dropout_prob": 0.0,
113
- "hidden_size": 768,
114
- "id2label": {
115
- "0": "LABEL_0",
116
- "1": "LABEL_1"
117
- },
118
- "image_size": 224,
119
- "initializer_range": 0.02,
120
- "intermediate_size": 3072,
121
- "is_decoder": false,
122
- "is_encoder_decoder": false,
123
- "label2id": {
124
- "LABEL_0": 0,
125
- "LABEL_1": 1
126
- },
127
- "layer_norm_eps": 1e-12,
128
- "length_penalty": 1.0,
129
- "max_length": 20,
130
- "min_length": 0,
131
- "model_type": "vit",
132
- "no_repeat_ngram_size": 0,
133
- "num_attention_heads": 12,
134
- "num_beam_groups": 1,
135
- "num_beams": 1,
136
- "num_channels": 3,
137
- "num_hidden_layers": 12,
138
- "num_return_sequences": 1,
139
- "output_attentions": false,
140
- "output_hidden_states": false,
141
- "output_scores": false,
142
- "pad_token_id": null,
143
- "patch_size": 16,
144
- "prefix": null,
145
- "problem_type": null,
146
- "pruned_heads": {},
147
- "remove_invalid_values": false,
148
- "repetition_penalty": 1.0,
149
- "return_dict": true,
150
- "return_dict_in_generate": false,
151
- "sep_token_id": null,
152
- "task_specific_params": null,
153
- "temperature": 1.0,
154
- "tie_encoder_decoder": false,
155
- "tie_word_embeddings": true,
156
- "tokenizer_class": null,
157
- "top_k": 50,
158
- "top_p": 1.0,
159
- "torch_dtype": null,
160
- "torchscript": false,
161
- "transformers_version": "4.11.0.dev0",
162
- "use_bfloat16": false
163
- },
164
- "eos_token_id": 50256,
165
- "is_encoder_decoder": true,
166
- "model_type": "vision-encoder-decoder",
167
- "pad_token_id": 50256,
168
- "transformers_version": null
169
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt_epoch_1_step_1500/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6205f82b78ca8b64ccdbeee07d61c460150faa8facd4bebaba1397a13f2fec4
3
- size 956799284
 
 
 
ckpt_epoch_1_step_1500/generation_eval.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_1500/merges.txt DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_1500/special_tokens_map.json DELETED
@@ -1 +0,0 @@
1
- {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
 
ckpt_epoch_1_step_1500/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_1500/tokenizer_config.json DELETED
@@ -1 +0,0 @@
1
- {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
 
ckpt_epoch_1_step_1500/vocab.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_1800/config.json DELETED
@@ -1,169 +0,0 @@
1
- {
2
- "architectures": [
3
- "VisionEncoderDecoderModel"
4
- ],
5
- "bos_token_id": 50256,
6
- "decoder": {
7
- "_name_or_path": "",
8
- "activation_function": "gelu_new",
9
- "add_cross_attention": true,
10
- "architectures": [
11
- "GPT2LMHeadModel"
12
- ],
13
- "attn_pdrop": 0.1,
14
- "bad_words_ids": null,
15
- "bos_token_id": 50256,
16
- "chunk_size_feed_forward": 0,
17
- "decoder_start_token_id": 50256,
18
- "diversity_penalty": 0.0,
19
- "do_sample": false,
20
- "early_stopping": false,
21
- "embd_pdrop": 0.1,
22
- "encoder_no_repeat_ngram_size": 0,
23
- "eos_token_id": 50256,
24
- "finetuning_task": null,
25
- "forced_bos_token_id": null,
26
- "forced_eos_token_id": null,
27
- "id2label": {
28
- "0": "LABEL_0",
29
- "1": "LABEL_1"
30
- },
31
- "initializer_range": 0.02,
32
- "is_decoder": true,
33
- "is_encoder_decoder": false,
34
- "label2id": {
35
- "LABEL_0": 0,
36
- "LABEL_1": 1
37
- },
38
- "layer_norm_epsilon": 1e-05,
39
- "length_penalty": 1.0,
40
- "max_length": 20,
41
- "min_length": 0,
42
- "model_type": "gpt2",
43
- "n_ctx": 1024,
44
- "n_embd": 768,
45
- "n_head": 12,
46
- "n_inner": null,
47
- "n_layer": 12,
48
- "n_positions": 1024,
49
- "no_repeat_ngram_size": 0,
50
- "num_beam_groups": 1,
51
- "num_beams": 1,
52
- "num_return_sequences": 1,
53
- "output_attentions": false,
54
- "output_hidden_states": false,
55
- "output_scores": false,
56
- "pad_token_id": 50256,
57
- "prefix": null,
58
- "problem_type": null,
59
- "pruned_heads": {},
60
- "remove_invalid_values": false,
61
- "repetition_penalty": 1.0,
62
- "resid_pdrop": 0.1,
63
- "return_dict": true,
64
- "return_dict_in_generate": false,
65
- "scale_attn_weights": true,
66
- "sep_token_id": null,
67
- "summary_activation": null,
68
- "summary_first_dropout": 0.1,
69
- "summary_proj_to_labels": true,
70
- "summary_type": "cls_index",
71
- "summary_use_proj": true,
72
- "task_specific_params": {
73
- "text-generation": {
74
- "do_sample": true,
75
- "max_length": 50
76
- }
77
- },
78
- "temperature": 1.0,
79
- "tie_encoder_decoder": false,
80
- "tie_word_embeddings": true,
81
- "tokenizer_class": null,
82
- "top_k": 50,
83
- "top_p": 1.0,
84
- "torch_dtype": null,
85
- "torchscript": false,
86
- "transformers_version": "4.11.0.dev0",
87
- "use_bfloat16": false,
88
- "use_cache": true,
89
- "vocab_size": 50257
90
- },
91
- "decoder_start_token_id": 50256,
92
- "encoder": {
93
- "_name_or_path": "",
94
- "add_cross_attention": false,
95
- "architectures": [
96
- "ViTModel"
97
- ],
98
- "attention_probs_dropout_prob": 0.0,
99
- "bad_words_ids": null,
100
- "bos_token_id": null,
101
- "chunk_size_feed_forward": 0,
102
- "decoder_start_token_id": null,
103
- "diversity_penalty": 0.0,
104
- "do_sample": false,
105
- "early_stopping": false,
106
- "encoder_no_repeat_ngram_size": 0,
107
- "eos_token_id": null,
108
- "finetuning_task": null,
109
- "forced_bos_token_id": null,
110
- "forced_eos_token_id": null,
111
- "hidden_act": "gelu",
112
- "hidden_dropout_prob": 0.0,
113
- "hidden_size": 768,
114
- "id2label": {
115
- "0": "LABEL_0",
116
- "1": "LABEL_1"
117
- },
118
- "image_size": 224,
119
- "initializer_range": 0.02,
120
- "intermediate_size": 3072,
121
- "is_decoder": false,
122
- "is_encoder_decoder": false,
123
- "label2id": {
124
- "LABEL_0": 0,
125
- "LABEL_1": 1
126
- },
127
- "layer_norm_eps": 1e-12,
128
- "length_penalty": 1.0,
129
- "max_length": 20,
130
- "min_length": 0,
131
- "model_type": "vit",
132
- "no_repeat_ngram_size": 0,
133
- "num_attention_heads": 12,
134
- "num_beam_groups": 1,
135
- "num_beams": 1,
136
- "num_channels": 3,
137
- "num_hidden_layers": 12,
138
- "num_return_sequences": 1,
139
- "output_attentions": false,
140
- "output_hidden_states": false,
141
- "output_scores": false,
142
- "pad_token_id": null,
143
- "patch_size": 16,
144
- "prefix": null,
145
- "problem_type": null,
146
- "pruned_heads": {},
147
- "remove_invalid_values": false,
148
- "repetition_penalty": 1.0,
149
- "return_dict": true,
150
- "return_dict_in_generate": false,
151
- "sep_token_id": null,
152
- "task_specific_params": null,
153
- "temperature": 1.0,
154
- "tie_encoder_decoder": false,
155
- "tie_word_embeddings": true,
156
- "tokenizer_class": null,
157
- "top_k": 50,
158
- "top_p": 1.0,
159
- "torch_dtype": null,
160
- "torchscript": false,
161
- "transformers_version": "4.11.0.dev0",
162
- "use_bfloat16": false
163
- },
164
- "eos_token_id": 50256,
165
- "is_encoder_decoder": true,
166
- "model_type": "vision-encoder-decoder",
167
- "pad_token_id": 50256,
168
- "transformers_version": null
169
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt_epoch_1_step_1800/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:490604c6d7dc47a49da3af020942b703f4c19999bb638959ed1dc922217101a1
3
- size 956799284
 
 
 
ckpt_epoch_1_step_1800/generation_eval.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_1800/merges.txt DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_1800/special_tokens_map.json DELETED
@@ -1 +0,0 @@
1
- {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
 
ckpt_epoch_1_step_1800/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_1800/tokenizer_config.json DELETED
@@ -1 +0,0 @@
1
- {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
 
ckpt_epoch_1_step_1800/vocab.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_2100/config.json DELETED
@@ -1,169 +0,0 @@
1
- {
2
- "architectures": [
3
- "VisionEncoderDecoderModel"
4
- ],
5
- "bos_token_id": 50256,
6
- "decoder": {
7
- "_name_or_path": "",
8
- "activation_function": "gelu_new",
9
- "add_cross_attention": true,
10
- "architectures": [
11
- "GPT2LMHeadModel"
12
- ],
13
- "attn_pdrop": 0.1,
14
- "bad_words_ids": null,
15
- "bos_token_id": 50256,
16
- "chunk_size_feed_forward": 0,
17
- "decoder_start_token_id": 50256,
18
- "diversity_penalty": 0.0,
19
- "do_sample": false,
20
- "early_stopping": false,
21
- "embd_pdrop": 0.1,
22
- "encoder_no_repeat_ngram_size": 0,
23
- "eos_token_id": 50256,
24
- "finetuning_task": null,
25
- "forced_bos_token_id": null,
26
- "forced_eos_token_id": null,
27
- "id2label": {
28
- "0": "LABEL_0",
29
- "1": "LABEL_1"
30
- },
31
- "initializer_range": 0.02,
32
- "is_decoder": true,
33
- "is_encoder_decoder": false,
34
- "label2id": {
35
- "LABEL_0": 0,
36
- "LABEL_1": 1
37
- },
38
- "layer_norm_epsilon": 1e-05,
39
- "length_penalty": 1.0,
40
- "max_length": 20,
41
- "min_length": 0,
42
- "model_type": "gpt2",
43
- "n_ctx": 1024,
44
- "n_embd": 768,
45
- "n_head": 12,
46
- "n_inner": null,
47
- "n_layer": 12,
48
- "n_positions": 1024,
49
- "no_repeat_ngram_size": 0,
50
- "num_beam_groups": 1,
51
- "num_beams": 1,
52
- "num_return_sequences": 1,
53
- "output_attentions": false,
54
- "output_hidden_states": false,
55
- "output_scores": false,
56
- "pad_token_id": 50256,
57
- "prefix": null,
58
- "problem_type": null,
59
- "pruned_heads": {},
60
- "remove_invalid_values": false,
61
- "repetition_penalty": 1.0,
62
- "resid_pdrop": 0.1,
63
- "return_dict": true,
64
- "return_dict_in_generate": false,
65
- "scale_attn_weights": true,
66
- "sep_token_id": null,
67
- "summary_activation": null,
68
- "summary_first_dropout": 0.1,
69
- "summary_proj_to_labels": true,
70
- "summary_type": "cls_index",
71
- "summary_use_proj": true,
72
- "task_specific_params": {
73
- "text-generation": {
74
- "do_sample": true,
75
- "max_length": 50
76
- }
77
- },
78
- "temperature": 1.0,
79
- "tie_encoder_decoder": false,
80
- "tie_word_embeddings": true,
81
- "tokenizer_class": null,
82
- "top_k": 50,
83
- "top_p": 1.0,
84
- "torch_dtype": null,
85
- "torchscript": false,
86
- "transformers_version": "4.11.0.dev0",
87
- "use_bfloat16": false,
88
- "use_cache": true,
89
- "vocab_size": 50257
90
- },
91
- "decoder_start_token_id": 50256,
92
- "encoder": {
93
- "_name_or_path": "",
94
- "add_cross_attention": false,
95
- "architectures": [
96
- "ViTModel"
97
- ],
98
- "attention_probs_dropout_prob": 0.0,
99
- "bad_words_ids": null,
100
- "bos_token_id": null,
101
- "chunk_size_feed_forward": 0,
102
- "decoder_start_token_id": null,
103
- "diversity_penalty": 0.0,
104
- "do_sample": false,
105
- "early_stopping": false,
106
- "encoder_no_repeat_ngram_size": 0,
107
- "eos_token_id": null,
108
- "finetuning_task": null,
109
- "forced_bos_token_id": null,
110
- "forced_eos_token_id": null,
111
- "hidden_act": "gelu",
112
- "hidden_dropout_prob": 0.0,
113
- "hidden_size": 768,
114
- "id2label": {
115
- "0": "LABEL_0",
116
- "1": "LABEL_1"
117
- },
118
- "image_size": 224,
119
- "initializer_range": 0.02,
120
- "intermediate_size": 3072,
121
- "is_decoder": false,
122
- "is_encoder_decoder": false,
123
- "label2id": {
124
- "LABEL_0": 0,
125
- "LABEL_1": 1
126
- },
127
- "layer_norm_eps": 1e-12,
128
- "length_penalty": 1.0,
129
- "max_length": 20,
130
- "min_length": 0,
131
- "model_type": "vit",
132
- "no_repeat_ngram_size": 0,
133
- "num_attention_heads": 12,
134
- "num_beam_groups": 1,
135
- "num_beams": 1,
136
- "num_channels": 3,
137
- "num_hidden_layers": 12,
138
- "num_return_sequences": 1,
139
- "output_attentions": false,
140
- "output_hidden_states": false,
141
- "output_scores": false,
142
- "pad_token_id": null,
143
- "patch_size": 16,
144
- "prefix": null,
145
- "problem_type": null,
146
- "pruned_heads": {},
147
- "remove_invalid_values": false,
148
- "repetition_penalty": 1.0,
149
- "return_dict": true,
150
- "return_dict_in_generate": false,
151
- "sep_token_id": null,
152
- "task_specific_params": null,
153
- "temperature": 1.0,
154
- "tie_encoder_decoder": false,
155
- "tie_word_embeddings": true,
156
- "tokenizer_class": null,
157
- "top_k": 50,
158
- "top_p": 1.0,
159
- "torch_dtype": null,
160
- "torchscript": false,
161
- "transformers_version": "4.11.0.dev0",
162
- "use_bfloat16": false
163
- },
164
- "eos_token_id": 50256,
165
- "is_encoder_decoder": true,
166
- "model_type": "vision-encoder-decoder",
167
- "pad_token_id": 50256,
168
- "transformers_version": null
169
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt_epoch_1_step_2100/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6ecc1d4c2b09a179d4daf54b604729dd2c27993d65762d6cbb4d042aa191df7
3
- size 956799284
 
 
 
ckpt_epoch_1_step_2100/generation_eval.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_2100/merges.txt DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_2100/special_tokens_map.json DELETED
@@ -1 +0,0 @@
1
- {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
 
ckpt_epoch_1_step_2100/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_2100/tokenizer_config.json DELETED
@@ -1 +0,0 @@
1
- {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
 
ckpt_epoch_1_step_2100/vocab.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_600/config.json DELETED
@@ -1,169 +0,0 @@
1
- {
2
- "architectures": [
3
- "VisionEncoderDecoderModel"
4
- ],
5
- "bos_token_id": 50256,
6
- "decoder": {
7
- "_name_or_path": "",
8
- "activation_function": "gelu_new",
9
- "add_cross_attention": true,
10
- "architectures": [
11
- "GPT2LMHeadModel"
12
- ],
13
- "attn_pdrop": 0.1,
14
- "bad_words_ids": null,
15
- "bos_token_id": 50256,
16
- "chunk_size_feed_forward": 0,
17
- "decoder_start_token_id": 50256,
18
- "diversity_penalty": 0.0,
19
- "do_sample": false,
20
- "early_stopping": false,
21
- "embd_pdrop": 0.1,
22
- "encoder_no_repeat_ngram_size": 0,
23
- "eos_token_id": 50256,
24
- "finetuning_task": null,
25
- "forced_bos_token_id": null,
26
- "forced_eos_token_id": null,
27
- "id2label": {
28
- "0": "LABEL_0",
29
- "1": "LABEL_1"
30
- },
31
- "initializer_range": 0.02,
32
- "is_decoder": true,
33
- "is_encoder_decoder": false,
34
- "label2id": {
35
- "LABEL_0": 0,
36
- "LABEL_1": 1
37
- },
38
- "layer_norm_epsilon": 1e-05,
39
- "length_penalty": 1.0,
40
- "max_length": 20,
41
- "min_length": 0,
42
- "model_type": "gpt2",
43
- "n_ctx": 1024,
44
- "n_embd": 768,
45
- "n_head": 12,
46
- "n_inner": null,
47
- "n_layer": 12,
48
- "n_positions": 1024,
49
- "no_repeat_ngram_size": 0,
50
- "num_beam_groups": 1,
51
- "num_beams": 1,
52
- "num_return_sequences": 1,
53
- "output_attentions": false,
54
- "output_hidden_states": false,
55
- "output_scores": false,
56
- "pad_token_id": 50256,
57
- "prefix": null,
58
- "problem_type": null,
59
- "pruned_heads": {},
60
- "remove_invalid_values": false,
61
- "repetition_penalty": 1.0,
62
- "resid_pdrop": 0.1,
63
- "return_dict": true,
64
- "return_dict_in_generate": false,
65
- "scale_attn_weights": true,
66
- "sep_token_id": null,
67
- "summary_activation": null,
68
- "summary_first_dropout": 0.1,
69
- "summary_proj_to_labels": true,
70
- "summary_type": "cls_index",
71
- "summary_use_proj": true,
72
- "task_specific_params": {
73
- "text-generation": {
74
- "do_sample": true,
75
- "max_length": 50
76
- }
77
- },
78
- "temperature": 1.0,
79
- "tie_encoder_decoder": false,
80
- "tie_word_embeddings": true,
81
- "tokenizer_class": null,
82
- "top_k": 50,
83
- "top_p": 1.0,
84
- "torch_dtype": null,
85
- "torchscript": false,
86
- "transformers_version": "4.11.0.dev0",
87
- "use_bfloat16": false,
88
- "use_cache": true,
89
- "vocab_size": 50257
90
- },
91
- "decoder_start_token_id": 50256,
92
- "encoder": {
93
- "_name_or_path": "",
94
- "add_cross_attention": false,
95
- "architectures": [
96
- "ViTModel"
97
- ],
98
- "attention_probs_dropout_prob": 0.0,
99
- "bad_words_ids": null,
100
- "bos_token_id": null,
101
- "chunk_size_feed_forward": 0,
102
- "decoder_start_token_id": null,
103
- "diversity_penalty": 0.0,
104
- "do_sample": false,
105
- "early_stopping": false,
106
- "encoder_no_repeat_ngram_size": 0,
107
- "eos_token_id": null,
108
- "finetuning_task": null,
109
- "forced_bos_token_id": null,
110
- "forced_eos_token_id": null,
111
- "hidden_act": "gelu",
112
- "hidden_dropout_prob": 0.0,
113
- "hidden_size": 768,
114
- "id2label": {
115
- "0": "LABEL_0",
116
- "1": "LABEL_1"
117
- },
118
- "image_size": 224,
119
- "initializer_range": 0.02,
120
- "intermediate_size": 3072,
121
- "is_decoder": false,
122
- "is_encoder_decoder": false,
123
- "label2id": {
124
- "LABEL_0": 0,
125
- "LABEL_1": 1
126
- },
127
- "layer_norm_eps": 1e-12,
128
- "length_penalty": 1.0,
129
- "max_length": 20,
130
- "min_length": 0,
131
- "model_type": "vit",
132
- "no_repeat_ngram_size": 0,
133
- "num_attention_heads": 12,
134
- "num_beam_groups": 1,
135
- "num_beams": 1,
136
- "num_channels": 3,
137
- "num_hidden_layers": 12,
138
- "num_return_sequences": 1,
139
- "output_attentions": false,
140
- "output_hidden_states": false,
141
- "output_scores": false,
142
- "pad_token_id": null,
143
- "patch_size": 16,
144
- "prefix": null,
145
- "problem_type": null,
146
- "pruned_heads": {},
147
- "remove_invalid_values": false,
148
- "repetition_penalty": 1.0,
149
- "return_dict": true,
150
- "return_dict_in_generate": false,
151
- "sep_token_id": null,
152
- "task_specific_params": null,
153
- "temperature": 1.0,
154
- "tie_encoder_decoder": false,
155
- "tie_word_embeddings": true,
156
- "tokenizer_class": null,
157
- "top_k": 50,
158
- "top_p": 1.0,
159
- "torch_dtype": null,
160
- "torchscript": false,
161
- "transformers_version": "4.11.0.dev0",
162
- "use_bfloat16": false
163
- },
164
- "eos_token_id": 50256,
165
- "is_encoder_decoder": true,
166
- "model_type": "vision-encoder-decoder",
167
- "pad_token_id": 50256,
168
- "transformers_version": null
169
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt_epoch_1_step_600/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fdc64df991b95360f18f2c1c957cfb20109e3cc8e7212699b7ebe8338a076bc
3
- size 956799284
 
 
 
ckpt_epoch_1_step_600/generation_eval.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_600/merges.txt DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_600/special_tokens_map.json DELETED
@@ -1 +0,0 @@
1
- {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
 
ckpt_epoch_1_step_600/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_600/tokenizer_config.json DELETED
@@ -1 +0,0 @@
1
- {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
 
ckpt_epoch_1_step_600/vocab.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_900/config.json DELETED
@@ -1,169 +0,0 @@
1
- {
2
- "architectures": [
3
- "VisionEncoderDecoderModel"
4
- ],
5
- "bos_token_id": 50256,
6
- "decoder": {
7
- "_name_or_path": "",
8
- "activation_function": "gelu_new",
9
- "add_cross_attention": true,
10
- "architectures": [
11
- "GPT2LMHeadModel"
12
- ],
13
- "attn_pdrop": 0.1,
14
- "bad_words_ids": null,
15
- "bos_token_id": 50256,
16
- "chunk_size_feed_forward": 0,
17
- "decoder_start_token_id": 50256,
18
- "diversity_penalty": 0.0,
19
- "do_sample": false,
20
- "early_stopping": false,
21
- "embd_pdrop": 0.1,
22
- "encoder_no_repeat_ngram_size": 0,
23
- "eos_token_id": 50256,
24
- "finetuning_task": null,
25
- "forced_bos_token_id": null,
26
- "forced_eos_token_id": null,
27
- "id2label": {
28
- "0": "LABEL_0",
29
- "1": "LABEL_1"
30
- },
31
- "initializer_range": 0.02,
32
- "is_decoder": true,
33
- "is_encoder_decoder": false,
34
- "label2id": {
35
- "LABEL_0": 0,
36
- "LABEL_1": 1
37
- },
38
- "layer_norm_epsilon": 1e-05,
39
- "length_penalty": 1.0,
40
- "max_length": 20,
41
- "min_length": 0,
42
- "model_type": "gpt2",
43
- "n_ctx": 1024,
44
- "n_embd": 768,
45
- "n_head": 12,
46
- "n_inner": null,
47
- "n_layer": 12,
48
- "n_positions": 1024,
49
- "no_repeat_ngram_size": 0,
50
- "num_beam_groups": 1,
51
- "num_beams": 1,
52
- "num_return_sequences": 1,
53
- "output_attentions": false,
54
- "output_hidden_states": false,
55
- "output_scores": false,
56
- "pad_token_id": 50256,
57
- "prefix": null,
58
- "problem_type": null,
59
- "pruned_heads": {},
60
- "remove_invalid_values": false,
61
- "repetition_penalty": 1.0,
62
- "resid_pdrop": 0.1,
63
- "return_dict": true,
64
- "return_dict_in_generate": false,
65
- "scale_attn_weights": true,
66
- "sep_token_id": null,
67
- "summary_activation": null,
68
- "summary_first_dropout": 0.1,
69
- "summary_proj_to_labels": true,
70
- "summary_type": "cls_index",
71
- "summary_use_proj": true,
72
- "task_specific_params": {
73
- "text-generation": {
74
- "do_sample": true,
75
- "max_length": 50
76
- }
77
- },
78
- "temperature": 1.0,
79
- "tie_encoder_decoder": false,
80
- "tie_word_embeddings": true,
81
- "tokenizer_class": null,
82
- "top_k": 50,
83
- "top_p": 1.0,
84
- "torch_dtype": null,
85
- "torchscript": false,
86
- "transformers_version": "4.11.0.dev0",
87
- "use_bfloat16": false,
88
- "use_cache": true,
89
- "vocab_size": 50257
90
- },
91
- "decoder_start_token_id": 50256,
92
- "encoder": {
93
- "_name_or_path": "",
94
- "add_cross_attention": false,
95
- "architectures": [
96
- "ViTModel"
97
- ],
98
- "attention_probs_dropout_prob": 0.0,
99
- "bad_words_ids": null,
100
- "bos_token_id": null,
101
- "chunk_size_feed_forward": 0,
102
- "decoder_start_token_id": null,
103
- "diversity_penalty": 0.0,
104
- "do_sample": false,
105
- "early_stopping": false,
106
- "encoder_no_repeat_ngram_size": 0,
107
- "eos_token_id": null,
108
- "finetuning_task": null,
109
- "forced_bos_token_id": null,
110
- "forced_eos_token_id": null,
111
- "hidden_act": "gelu",
112
- "hidden_dropout_prob": 0.0,
113
- "hidden_size": 768,
114
- "id2label": {
115
- "0": "LABEL_0",
116
- "1": "LABEL_1"
117
- },
118
- "image_size": 224,
119
- "initializer_range": 0.02,
120
- "intermediate_size": 3072,
121
- "is_decoder": false,
122
- "is_encoder_decoder": false,
123
- "label2id": {
124
- "LABEL_0": 0,
125
- "LABEL_1": 1
126
- },
127
- "layer_norm_eps": 1e-12,
128
- "length_penalty": 1.0,
129
- "max_length": 20,
130
- "min_length": 0,
131
- "model_type": "vit",
132
- "no_repeat_ngram_size": 0,
133
- "num_attention_heads": 12,
134
- "num_beam_groups": 1,
135
- "num_beams": 1,
136
- "num_channels": 3,
137
- "num_hidden_layers": 12,
138
- "num_return_sequences": 1,
139
- "output_attentions": false,
140
- "output_hidden_states": false,
141
- "output_scores": false,
142
- "pad_token_id": null,
143
- "patch_size": 16,
144
- "prefix": null,
145
- "problem_type": null,
146
- "pruned_heads": {},
147
- "remove_invalid_values": false,
148
- "repetition_penalty": 1.0,
149
- "return_dict": true,
150
- "return_dict_in_generate": false,
151
- "sep_token_id": null,
152
- "task_specific_params": null,
153
- "temperature": 1.0,
154
- "tie_encoder_decoder": false,
155
- "tie_word_embeddings": true,
156
- "tokenizer_class": null,
157
- "top_k": 50,
158
- "top_p": 1.0,
159
- "torch_dtype": null,
160
- "torchscript": false,
161
- "transformers_version": "4.11.0.dev0",
162
- "use_bfloat16": false
163
- },
164
- "eos_token_id": 50256,
165
- "is_encoder_decoder": true,
166
- "model_type": "vision-encoder-decoder",
167
- "pad_token_id": 50256,
168
- "transformers_version": null
169
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt_epoch_1_step_900/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1d0b927e570231d347e00243681983d57d4f3e538cc11a9068639e9238e6589
3
- size 956799284
 
 
 
ckpt_epoch_1_step_900/generation_eval.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_900/merges.txt DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_900/special_tokens_map.json DELETED
@@ -1 +0,0 @@
1
- {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
 
ckpt_epoch_1_step_900/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_1_step_900/tokenizer_config.json DELETED
@@ -1 +0,0 @@
1
- {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
 
ckpt_epoch_1_step_900/vocab.json DELETED
The diff for this file is too large to render. See raw diff
ckpt_epoch_2_step_2400/config.json DELETED
@@ -1,169 +0,0 @@
1
- {
2
- "architectures": [
3
- "VisionEncoderDecoderModel"
4
- ],
5
- "bos_token_id": 50256,
6
- "decoder": {
7
- "_name_or_path": "",
8
- "activation_function": "gelu_new",
9
- "add_cross_attention": true,
10
- "architectures": [
11
- "GPT2LMHeadModel"
12
- ],
13
- "attn_pdrop": 0.1,
14
- "bad_words_ids": null,
15
- "bos_token_id": 50256,
16
- "chunk_size_feed_forward": 0,
17
- "decoder_start_token_id": 50256,
18
- "diversity_penalty": 0.0,
19
- "do_sample": false,
20
- "early_stopping": false,
21
- "embd_pdrop": 0.1,
22
- "encoder_no_repeat_ngram_size": 0,
23
- "eos_token_id": 50256,
24
- "finetuning_task": null,
25
- "forced_bos_token_id": null,
26
- "forced_eos_token_id": null,
27
- "id2label": {
28
- "0": "LABEL_0",
29
- "1": "LABEL_1"
30
- },
31
- "initializer_range": 0.02,
32
- "is_decoder": true,
33
- "is_encoder_decoder": false,
34
- "label2id": {
35
- "LABEL_0": 0,
36
- "LABEL_1": 1
37
- },
38
- "layer_norm_epsilon": 1e-05,
39
- "length_penalty": 1.0,
40
- "max_length": 20,
41
- "min_length": 0,
42
- "model_type": "gpt2",
43
- "n_ctx": 1024,
44
- "n_embd": 768,
45
- "n_head": 12,
46
- "n_inner": null,
47
- "n_layer": 12,
48
- "n_positions": 1024,
49
- "no_repeat_ngram_size": 0,
50
- "num_beam_groups": 1,
51
- "num_beams": 1,
52
- "num_return_sequences": 1,
53
- "output_attentions": false,
54
- "output_hidden_states": false,
55
- "output_scores": false,
56
- "pad_token_id": 50256,
57
- "prefix": null,
58
- "problem_type": null,
59
- "pruned_heads": {},
60
- "remove_invalid_values": false,
61
- "repetition_penalty": 1.0,
62
- "resid_pdrop": 0.1,
63
- "return_dict": true,
64
- "return_dict_in_generate": false,
65
- "scale_attn_weights": true,
66
- "sep_token_id": null,
67
- "summary_activation": null,
68
- "summary_first_dropout": 0.1,
69
- "summary_proj_to_labels": true,
70
- "summary_type": "cls_index",
71
- "summary_use_proj": true,
72
- "task_specific_params": {
73
- "text-generation": {
74
- "do_sample": true,
75
- "max_length": 50
76
- }
77
- },
78
- "temperature": 1.0,
79
- "tie_encoder_decoder": false,
80
- "tie_word_embeddings": true,
81
- "tokenizer_class": null,
82
- "top_k": 50,
83
- "top_p": 1.0,
84
- "torch_dtype": null,
85
- "torchscript": false,
86
- "transformers_version": "4.11.0.dev0",
87
- "use_bfloat16": false,
88
- "use_cache": true,
89
- "vocab_size": 50257
90
- },
91
- "decoder_start_token_id": 50256,
92
- "encoder": {
93
- "_name_or_path": "",
94
- "add_cross_attention": false,
95
- "architectures": [
96
- "ViTModel"
97
- ],
98
- "attention_probs_dropout_prob": 0.0,
99
- "bad_words_ids": null,
100
- "bos_token_id": null,
101
- "chunk_size_feed_forward": 0,
102
- "decoder_start_token_id": null,
103
- "diversity_penalty": 0.0,
104
- "do_sample": false,
105
- "early_stopping": false,
106
- "encoder_no_repeat_ngram_size": 0,
107
- "eos_token_id": null,
108
- "finetuning_task": null,
109
- "forced_bos_token_id": null,
110
- "forced_eos_token_id": null,
111
- "hidden_act": "gelu",
112
- "hidden_dropout_prob": 0.0,
113
- "hidden_size": 768,
114
- "id2label": {
115
- "0": "LABEL_0",
116
- "1": "LABEL_1"
117
- },
118
- "image_size": 224,
119
- "initializer_range": 0.02,
120
- "intermediate_size": 3072,
121
- "is_decoder": false,
122
- "is_encoder_decoder": false,
123
- "label2id": {
124
- "LABEL_0": 0,
125
- "LABEL_1": 1
126
- },
127
- "layer_norm_eps": 1e-12,
128
- "length_penalty": 1.0,
129
- "max_length": 20,
130
- "min_length": 0,
131
- "model_type": "vit",
132
- "no_repeat_ngram_size": 0,
133
- "num_attention_heads": 12,
134
- "num_beam_groups": 1,
135
- "num_beams": 1,
136
- "num_channels": 3,
137
- "num_hidden_layers": 12,
138
- "num_return_sequences": 1,
139
- "output_attentions": false,
140
- "output_hidden_states": false,
141
- "output_scores": false,
142
- "pad_token_id": null,
143
- "patch_size": 16,
144
- "prefix": null,
145
- "problem_type": null,
146
- "pruned_heads": {},
147
- "remove_invalid_values": false,
148
- "repetition_penalty": 1.0,
149
- "return_dict": true,
150
- "return_dict_in_generate": false,
151
- "sep_token_id": null,
152
- "task_specific_params": null,
153
- "temperature": 1.0,
154
- "tie_encoder_decoder": false,
155
- "tie_word_embeddings": true,
156
- "tokenizer_class": null,
157
- "top_k": 50,
158
- "top_p": 1.0,
159
- "torch_dtype": null,
160
- "torchscript": false,
161
- "transformers_version": "4.11.0.dev0",
162
- "use_bfloat16": false
163
- },
164
- "eos_token_id": 50256,
165
- "is_encoder_decoder": true,
166
- "model_type": "vision-encoder-decoder",
167
- "pad_token_id": 50256,
168
- "transformers_version": null
169
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt_epoch_2_step_2400/flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4feb497b73eb7978ca6794711496428734919819ebc09184e422df0fb49ccfce
3
- size 956799284