Hugging Face's logo

shaheen6
/
pixel_translation

Model card Files
xet
 Community
Abdelrahman Shaheen commited on
Commit
d12eb98
·
1 Parent(s): f54f297

initial

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-8000/config.json +192 -0
  2. checkpoint-8000/merges.txt +0 -0
  3. checkpoint-8000/optimizer.pt +3 -0
  4. checkpoint-8000/pytorch_model.bin +3 -0
  5. checkpoint-8000/rng_state.pth +3 -0
  6. checkpoint-8000/scaler.pt +3 -0
  7. checkpoint-8000/scheduler.pt +3 -0
  8. checkpoint-8000/special_tokens_map.json +1 -0
  9. checkpoint-8000/tokenizer.json +0 -0
  10. checkpoint-8000/tokenizer_config.json +1 -0
  11. checkpoint-8000/trainer_state.json +0 -0
  12. checkpoint-8000/training_args.bin +3 -0
  13. checkpoint-8000/vocab.json +0 -0
  14. checkpoint-8200/config.json +192 -0
  15. checkpoint-8200/merges.txt +0 -0
  16. checkpoint-8200/optimizer.pt +3 -0
  17. checkpoint-8200/pytorch_model.bin +3 -0
  18. checkpoint-8200/rng_state.pth +3 -0
  19. checkpoint-8200/scaler.pt +3 -0
  20. checkpoint-8200/scheduler.pt +3 -0
  21. checkpoint-8200/special_tokens_map.json +1 -0
  22. checkpoint-8200/tokenizer.json +0 -0
  23. checkpoint-8200/tokenizer_config.json +1 -0
  24. checkpoint-8200/trainer_state.json +0 -0
  25. checkpoint-8200/training_args.bin +3 -0
  26. checkpoint-8200/vocab.json +0 -0
  27. checkpoint-8400/config.json +192 -0
  28. checkpoint-8400/merges.txt +0 -0
  29. checkpoint-8400/optimizer.pt +3 -0
  30. checkpoint-8400/pytorch_model.bin +3 -0
  31. checkpoint-8400/rng_state.pth +3 -0
  32. checkpoint-8400/scaler.pt +3 -0
  33. checkpoint-8400/scheduler.pt +3 -0
  34. checkpoint-8400/special_tokens_map.json +1 -0
  35. checkpoint-8400/tokenizer.json +0 -0
  36. checkpoint-8400/tokenizer_config.json +1 -0
  37. checkpoint-8400/trainer_state.json +0 -0
  38. checkpoint-8400/training_args.bin +3 -0
  39. checkpoint-8400/vocab.json +0 -0
  40. checkpoint-8600/config.json +192 -0
  41. checkpoint-8600/merges.txt +0 -0
  42. checkpoint-8600/optimizer.pt +3 -0
  43. checkpoint-8600/pytorch_model.bin +3 -0
  44. checkpoint-8600/rng_state.pth +3 -0
  45. checkpoint-8600/scaler.pt +3 -0
  46. checkpoint-8600/scheduler.pt +3 -0
  47. checkpoint-8600/special_tokens_map.json +1 -0
  48. checkpoint-8600/tokenizer.json +0 -0
  49. checkpoint-8600/tokenizer_config.json +1 -0
  50. checkpoint-8600/trainer_state.json +0 -0
checkpoint-8000/config.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "PIXELSumModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "gpt2",
7
+ "activation_function": "gelu_new",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "GPT2LMHeadModel"
11
+ ],
12
+ "attn_pdrop": 0.1,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": 50256,
15
+ "chunk_size_feed_forward": 0,
16
+ "cross_attention_hidden_size": null,
17
+ "cross_attention_reduce_factor": 1,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "embd_pdrop": 0.1,
23
+ "encoder_hidden_size": 768,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 50256,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_epsilon": 1e-05,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "min_length": 0,
45
+ "model_type": "gpt2",
46
+ "n_ctx": 1024,
47
+ "n_embd": 768,
48
+ "n_head": 12,
49
+ "n_inner": null,
50
+ "n_layer": 12,
51
+ "n_positions": 1024,
52
+ "no_repeat_ngram_size": 0,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": null,
60
+ "prefix": null,
61
+ "problem_type": null,
62
+ "pruned_heads": {},
63
+ "remove_invalid_values": false,
64
+ "reorder_and_upcast_attn": false,
65
+ "repetition_penalty": 1.0,
66
+ "resid_pdrop": 0.1,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "scale_attn_by_inverse_layer_idx": false,
70
+ "scale_attn_weights": true,
71
+ "sep_token_id": null,
72
+ "summary_activation": null,
73
+ "summary_first_dropout": 0.1,
74
+ "summary_proj_to_labels": true,
75
+ "summary_type": "cls_index",
76
+ "summary_use_proj": true,
77
+ "task_specific_params": {
78
+ "text-generation": {
79
+ "do_sample": true,
80
+ "max_length": 64
81
+ }
82
+ },
83
+ "temperature": 1.0,
84
+ "tie_encoder_decoder": false,
85
+ "tie_word_embeddings": true,
86
+ "tokenizer_class": null,
87
+ "top_k": 50,
88
+ "top_p": 1.0,
89
+ "torch_dtype": null,
90
+ "torchscript": false,
91
+ "transformers_version": "4.19.0",
92
+ "typical_p": 1.0,
93
+ "use_bfloat16": false,
94
+ "use_cache": true,
95
+ "vocab_size": 50257
96
+ },
97
+ "decoder_start_token_id": 50256,
98
+ "encoder": {
99
+ "_name_or_path": "/home/Abdelrahman.Shaheen@mbzuai.ac.ae/pixel-m4",
100
+ "add_cross_attention": false,
101
+ "architectures": [
102
+ "PIXELForPreTraining"
103
+ ],
104
+ "attention_probs_dropout_prob": 0.1,
105
+ "bad_words_ids": null,
106
+ "bos_token_id": null,
107
+ "chunk_size_feed_forward": 0,
108
+ "cross_attention_hidden_size": null,
109
+ "decoder_hidden_size": 512,
110
+ "decoder_intermediate_size": 2048,
111
+ "decoder_num_attention_heads": 16,
112
+ "decoder_num_hidden_layers": 8,
113
+ "decoder_start_token_id": null,
114
+ "diversity_penalty": 0.0,
115
+ "do_eval": true,
116
+ "do_sample": false,
117
+ "early_stopping": false,
118
+ "encoder_no_repeat_ngram_size": 0,
119
+ "eos_token_id": null,
120
+ "exponential_decay_length_penalty": null,
121
+ "finetuning_task": null,
122
+ "forced_bos_token_id": null,
123
+ "forced_eos_token_id": null,
124
+ "hidden_act": "gelu",
125
+ "hidden_dropout_prob": 0.1,
126
+ "hidden_size": 768,
127
+ "id2label": {
128
+ "0": "LABEL_0",
129
+ "1": "LABEL_1"
130
+ },
131
+ "image_size": [
132
+ 16,
133
+ 8464
134
+ ],
135
+ "initializer_range": 0.02,
136
+ "intermediate_size": 3072,
137
+ "is_decoder": false,
138
+ "is_encoder_decoder": false,
139
+ "label2id": {
140
+ "LABEL_0": 0,
141
+ "LABEL_1": 1
142
+ },
143
+ "layer_norm_eps": 1e-12,
144
+ "length_penalty": 1.0,
145
+ "mask_ratio": 0.25,
146
+ "max_length": 20,
147
+ "min_length": 0,
148
+ "model_type": "pixel",
149
+ "no_repeat_ngram_size": 0,
150
+ "norm_pix_loss": true,
151
+ "num_attention_heads": 12,
152
+ "num_beam_groups": 1,
153
+ "num_beams": 1,
154
+ "num_channels": 3,
155
+ "num_hidden_layers": 12,
156
+ "num_return_sequences": 1,
157
+ "output_attentions": false,
158
+ "output_hidden_states": false,
159
+ "output_scores": false,
160
+ "pad_token_id": null,
161
+ "patch_size": 16,
162
+ "prefix": null,
163
+ "problem_type": null,
164
+ "pruned_heads": {},
165
+ "qkv_bias": true,
166
+ "remove_invalid_values": false,
167
+ "repetition_penalty": 1.0,
168
+ "return_dict": true,
169
+ "return_dict_in_generate": false,
170
+ "sep_token_id": null,
171
+ "task_specific_params": null,
172
+ "temperature": 1.0,
173
+ "tie_encoder_decoder": false,
174
+ "tie_word_embeddings": true,
175
+ "tokenizer_class": null,
176
+ "top_k": 50,
177
+ "top_p": 1.0,
178
+ "torch_dtype": "float32",
179
+ "torchscript": false,
180
+ "transformers_version": "4.19.0",
181
+ "typical_p": 1.0,
182
+ "use_bfloat16": false
183
+ },
184
+ "eos_token_id": 50256,
185
+ "is_encoder_decoder": true,
186
+ "model_type": "pixelsum",
187
+ "pad_token_id": 50256,
188
+ "tie_word_embeddings": false,
189
+ "torch_dtype": "float32",
190
+ "transformers_version": null,
191
+ "vocab_size": 50257
192
+ }
checkpoint-8000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b06d5edd1f5e24cb208961795a80b6cc8ef5d0eb720766ac0915fa2c6eb18661
3
+ size 1911148602
checkpoint-8000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b56c81eb4e7c8426b2e5cfce9bf0616f38216eeb1311c93d7b4047d9ce6503f4
3
+ size 980777906
checkpoint-8000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c61f6de9a2b72136fc11aed7a02781277979281a181f583041f862fc1efcd67
3
+ size 14498
checkpoint-8000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76aebad89d27920e0c2149ad0f0bc409d36a4a6e93f83ef43eb8dc83cdd04f1
3
+ size 988
checkpoint-8000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4696f4023a447f30d8dfbadde4889afe2b4646dc65162409a4af6d8cad03f33
3
+ size 1064
checkpoint-8000/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|pad|>"}
checkpoint-8000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8000/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
checkpoint-8000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b670838dea50fec9ce0dd42852da7e6c1415575a4da891fa82245fd11272b227
3
+ size 3896
checkpoint-8000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8200/config.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "PIXELSumModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "gpt2",
7
+ "activation_function": "gelu_new",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "GPT2LMHeadModel"
11
+ ],
12
+ "attn_pdrop": 0.1,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": 50256,
15
+ "chunk_size_feed_forward": 0,
16
+ "cross_attention_hidden_size": null,
17
+ "cross_attention_reduce_factor": 1,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "embd_pdrop": 0.1,
23
+ "encoder_hidden_size": 768,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 50256,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_epsilon": 1e-05,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "min_length": 0,
45
+ "model_type": "gpt2",
46
+ "n_ctx": 1024,
47
+ "n_embd": 768,
48
+ "n_head": 12,
49
+ "n_inner": null,
50
+ "n_layer": 12,
51
+ "n_positions": 1024,
52
+ "no_repeat_ngram_size": 0,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": null,
60
+ "prefix": null,
61
+ "problem_type": null,
62
+ "pruned_heads": {},
63
+ "remove_invalid_values": false,
64
+ "reorder_and_upcast_attn": false,
65
+ "repetition_penalty": 1.0,
66
+ "resid_pdrop": 0.1,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "scale_attn_by_inverse_layer_idx": false,
70
+ "scale_attn_weights": true,
71
+ "sep_token_id": null,
72
+ "summary_activation": null,
73
+ "summary_first_dropout": 0.1,
74
+ "summary_proj_to_labels": true,
75
+ "summary_type": "cls_index",
76
+ "summary_use_proj": true,
77
+ "task_specific_params": {
78
+ "text-generation": {
79
+ "do_sample": true,
80
+ "max_length": 64
81
+ }
82
+ },
83
+ "temperature": 1.0,
84
+ "tie_encoder_decoder": false,
85
+ "tie_word_embeddings": true,
86
+ "tokenizer_class": null,
87
+ "top_k": 50,
88
+ "top_p": 1.0,
89
+ "torch_dtype": null,
90
+ "torchscript": false,
91
+ "transformers_version": "4.19.0",
92
+ "typical_p": 1.0,
93
+ "use_bfloat16": false,
94
+ "use_cache": true,
95
+ "vocab_size": 50257
96
+ },
97
+ "decoder_start_token_id": 50256,
98
+ "encoder": {
99
+ "_name_or_path": "/home/Abdelrahman.Shaheen@mbzuai.ac.ae/pixel-m4",
100
+ "add_cross_attention": false,
101
+ "architectures": [
102
+ "PIXELForPreTraining"
103
+ ],
104
+ "attention_probs_dropout_prob": 0.1,
105
+ "bad_words_ids": null,
106
+ "bos_token_id": null,
107
+ "chunk_size_feed_forward": 0,
108
+ "cross_attention_hidden_size": null,
109
+ "decoder_hidden_size": 512,
110
+ "decoder_intermediate_size": 2048,
111
+ "decoder_num_attention_heads": 16,
112
+ "decoder_num_hidden_layers": 8,
113
+ "decoder_start_token_id": null,
114
+ "diversity_penalty": 0.0,
115
+ "do_eval": true,
116
+ "do_sample": false,
117
+ "early_stopping": false,
118
+ "encoder_no_repeat_ngram_size": 0,
119
+ "eos_token_id": null,
120
+ "exponential_decay_length_penalty": null,
121
+ "finetuning_task": null,
122
+ "forced_bos_token_id": null,
123
+ "forced_eos_token_id": null,
124
+ "hidden_act": "gelu",
125
+ "hidden_dropout_prob": 0.1,
126
+ "hidden_size": 768,
127
+ "id2label": {
128
+ "0": "LABEL_0",
129
+ "1": "LABEL_1"
130
+ },
131
+ "image_size": [
132
+ 16,
133
+ 8464
134
+ ],
135
+ "initializer_range": 0.02,
136
+ "intermediate_size": 3072,
137
+ "is_decoder": false,
138
+ "is_encoder_decoder": false,
139
+ "label2id": {
140
+ "LABEL_0": 0,
141
+ "LABEL_1": 1
142
+ },
143
+ "layer_norm_eps": 1e-12,
144
+ "length_penalty": 1.0,
145
+ "mask_ratio": 0.25,
146
+ "max_length": 20,
147
+ "min_length": 0,
148
+ "model_type": "pixel",
149
+ "no_repeat_ngram_size": 0,
150
+ "norm_pix_loss": true,
151
+ "num_attention_heads": 12,
152
+ "num_beam_groups": 1,
153
+ "num_beams": 1,
154
+ "num_channels": 3,
155
+ "num_hidden_layers": 12,
156
+ "num_return_sequences": 1,
157
+ "output_attentions": false,
158
+ "output_hidden_states": false,
159
+ "output_scores": false,
160
+ "pad_token_id": null,
161
+ "patch_size": 16,
162
+ "prefix": null,
163
+ "problem_type": null,
164
+ "pruned_heads": {},
165
+ "qkv_bias": true,
166
+ "remove_invalid_values": false,
167
+ "repetition_penalty": 1.0,
168
+ "return_dict": true,
169
+ "return_dict_in_generate": false,
170
+ "sep_token_id": null,
171
+ "task_specific_params": null,
172
+ "temperature": 1.0,
173
+ "tie_encoder_decoder": false,
174
+ "tie_word_embeddings": true,
175
+ "tokenizer_class": null,
176
+ "top_k": 50,
177
+ "top_p": 1.0,
178
+ "torch_dtype": "float32",
179
+ "torchscript": false,
180
+ "transformers_version": "4.19.0",
181
+ "typical_p": 1.0,
182
+ "use_bfloat16": false
183
+ },
184
+ "eos_token_id": 50256,
185
+ "is_encoder_decoder": true,
186
+ "model_type": "pixelsum",
187
+ "pad_token_id": 50256,
188
+ "tie_word_embeddings": false,
189
+ "torch_dtype": "float32",
190
+ "transformers_version": null,
191
+ "vocab_size": 50257
192
+ }
checkpoint-8200/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:673f27990c5ac411dafdbceb20d0493c2d1d5177a88c77e8afab620805f69c8c
3
+ size 1911148602
checkpoint-8200/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:933f1bc2e8db076e303476cf24d48c1f95d117af6fd86445dbbb7c9fd40021f4
3
+ size 980777906
checkpoint-8200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b5e63f6f44a2bb6644ab75aa394dc3c252b9f1959c62e16bf0cdc0f35b04b95
3
+ size 14498
checkpoint-8200/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13f66182781584c72ffb511da22c174501390503b15a9d6460f05de5055a2c45
3
+ size 988
checkpoint-8200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ae32594cf288c2dde9396d6d7d0efc41b10aaa98602c6e8f7fbb3aadf5c62d9
3
+ size 1064
checkpoint-8200/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|pad|>"}
checkpoint-8200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8200/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
checkpoint-8200/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b670838dea50fec9ce0dd42852da7e6c1415575a4da891fa82245fd11272b227
3
+ size 3896
checkpoint-8200/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8400/config.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "PIXELSumModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "gpt2",
7
+ "activation_function": "gelu_new",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "GPT2LMHeadModel"
11
+ ],
12
+ "attn_pdrop": 0.1,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": 50256,
15
+ "chunk_size_feed_forward": 0,
16
+ "cross_attention_hidden_size": null,
17
+ "cross_attention_reduce_factor": 1,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "embd_pdrop": 0.1,
23
+ "encoder_hidden_size": 768,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 50256,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_epsilon": 1e-05,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "min_length": 0,
45
+ "model_type": "gpt2",
46
+ "n_ctx": 1024,
47
+ "n_embd": 768,
48
+ "n_head": 12,
49
+ "n_inner": null,
50
+ "n_layer": 12,
51
+ "n_positions": 1024,
52
+ "no_repeat_ngram_size": 0,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": null,
60
+ "prefix": null,
61
+ "problem_type": null,
62
+ "pruned_heads": {},
63
+ "remove_invalid_values": false,
64
+ "reorder_and_upcast_attn": false,
65
+ "repetition_penalty": 1.0,
66
+ "resid_pdrop": 0.1,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "scale_attn_by_inverse_layer_idx": false,
70
+ "scale_attn_weights": true,
71
+ "sep_token_id": null,
72
+ "summary_activation": null,
73
+ "summary_first_dropout": 0.1,
74
+ "summary_proj_to_labels": true,
75
+ "summary_type": "cls_index",
76
+ "summary_use_proj": true,
77
+ "task_specific_params": {
78
+ "text-generation": {
79
+ "do_sample": true,
80
+ "max_length": 64
81
+ }
82
+ },
83
+ "temperature": 1.0,
84
+ "tie_encoder_decoder": false,
85
+ "tie_word_embeddings": true,
86
+ "tokenizer_class": null,
87
+ "top_k": 50,
88
+ "top_p": 1.0,
89
+ "torch_dtype": null,
90
+ "torchscript": false,
91
+ "transformers_version": "4.19.0",
92
+ "typical_p": 1.0,
93
+ "use_bfloat16": false,
94
+ "use_cache": true,
95
+ "vocab_size": 50257
96
+ },
97
+ "decoder_start_token_id": 50256,
98
+ "encoder": {
99
+ "_name_or_path": "/home/Abdelrahman.Shaheen@mbzuai.ac.ae/pixel-m4",
100
+ "add_cross_attention": false,
101
+ "architectures": [
102
+ "PIXELForPreTraining"
103
+ ],
104
+ "attention_probs_dropout_prob": 0.1,
105
+ "bad_words_ids": null,
106
+ "bos_token_id": null,
107
+ "chunk_size_feed_forward": 0,
108
+ "cross_attention_hidden_size": null,
109
+ "decoder_hidden_size": 512,
110
+ "decoder_intermediate_size": 2048,
111
+ "decoder_num_attention_heads": 16,
112
+ "decoder_num_hidden_layers": 8,
113
+ "decoder_start_token_id": null,
114
+ "diversity_penalty": 0.0,
115
+ "do_eval": true,
116
+ "do_sample": false,
117
+ "early_stopping": false,
118
+ "encoder_no_repeat_ngram_size": 0,
119
+ "eos_token_id": null,
120
+ "exponential_decay_length_penalty": null,
121
+ "finetuning_task": null,
122
+ "forced_bos_token_id": null,
123
+ "forced_eos_token_id": null,
124
+ "hidden_act": "gelu",
125
+ "hidden_dropout_prob": 0.1,
126
+ "hidden_size": 768,
127
+ "id2label": {
128
+ "0": "LABEL_0",
129
+ "1": "LABEL_1"
130
+ },
131
+ "image_size": [
132
+ 16,
133
+ 8464
134
+ ],
135
+ "initializer_range": 0.02,
136
+ "intermediate_size": 3072,
137
+ "is_decoder": false,
138
+ "is_encoder_decoder": false,
139
+ "label2id": {
140
+ "LABEL_0": 0,
141
+ "LABEL_1": 1
142
+ },
143
+ "layer_norm_eps": 1e-12,
144
+ "length_penalty": 1.0,
145
+ "mask_ratio": 0.25,
146
+ "max_length": 20,
147
+ "min_length": 0,
148
+ "model_type": "pixel",
149
+ "no_repeat_ngram_size": 0,
150
+ "norm_pix_loss": true,
151
+ "num_attention_heads": 12,
152
+ "num_beam_groups": 1,
153
+ "num_beams": 1,
154
+ "num_channels": 3,
155
+ "num_hidden_layers": 12,
156
+ "num_return_sequences": 1,
157
+ "output_attentions": false,
158
+ "output_hidden_states": false,
159
+ "output_scores": false,
160
+ "pad_token_id": null,
161
+ "patch_size": 16,
162
+ "prefix": null,
163
+ "problem_type": null,
164
+ "pruned_heads": {},
165
+ "qkv_bias": true,
166
+ "remove_invalid_values": false,
167
+ "repetition_penalty": 1.0,
168
+ "return_dict": true,
169
+ "return_dict_in_generate": false,
170
+ "sep_token_id": null,
171
+ "task_specific_params": null,
172
+ "temperature": 1.0,
173
+ "tie_encoder_decoder": false,
174
+ "tie_word_embeddings": true,
175
+ "tokenizer_class": null,
176
+ "top_k": 50,
177
+ "top_p": 1.0,
178
+ "torch_dtype": "float32",
179
+ "torchscript": false,
180
+ "transformers_version": "4.19.0",
181
+ "typical_p": 1.0,
182
+ "use_bfloat16": false
183
+ },
184
+ "eos_token_id": 50256,
185
+ "is_encoder_decoder": true,
186
+ "model_type": "pixelsum",
187
+ "pad_token_id": 50256,
188
+ "tie_word_embeddings": false,
189
+ "torch_dtype": "float32",
190
+ "transformers_version": null,
191
+ "vocab_size": 50257
192
+ }
checkpoint-8400/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55cdd5eb32f4ba62d726151969395a09f0843b9b66eed5a139dd0d6db1b82725
3
+ size 1911148602
checkpoint-8400/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add3b4cf47cb37f0540dd59f32e6f1e86a41d2c20d247b380bc26616564f58f4
3
+ size 980777906
checkpoint-8400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5b1b4467820ef993bad614d1b99e1740a021b0236f3f2e43294e8ac31c91f55
3
+ size 14498
checkpoint-8400/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe68b923544b9f90182298563948de85054162f0d48975aabe2f7817d7e2701
3
+ size 988
checkpoint-8400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0d4c9aa997dba3e6cf24bfd94f97826d76bb64d4fd0df5d49f2b6446d61a919
3
+ size 1064
checkpoint-8400/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|pad|>"}
checkpoint-8400/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8400/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
checkpoint-8400/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b670838dea50fec9ce0dd42852da7e6c1415575a4da891fa82245fd11272b227
3
+ size 3896
checkpoint-8400/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8600/config.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "PIXELSumModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "gpt2",
7
+ "activation_function": "gelu_new",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "GPT2LMHeadModel"
11
+ ],
12
+ "attn_pdrop": 0.1,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": 50256,
15
+ "chunk_size_feed_forward": 0,
16
+ "cross_attention_hidden_size": null,
17
+ "cross_attention_reduce_factor": 1,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "embd_pdrop": 0.1,
23
+ "encoder_hidden_size": 768,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 50256,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_epsilon": 1e-05,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "min_length": 0,
45
+ "model_type": "gpt2",
46
+ "n_ctx": 1024,
47
+ "n_embd": 768,
48
+ "n_head": 12,
49
+ "n_inner": null,
50
+ "n_layer": 12,
51
+ "n_positions": 1024,
52
+ "no_repeat_ngram_size": 0,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": null,
60
+ "prefix": null,
61
+ "problem_type": null,
62
+ "pruned_heads": {},
63
+ "remove_invalid_values": false,
64
+ "reorder_and_upcast_attn": false,
65
+ "repetition_penalty": 1.0,
66
+ "resid_pdrop": 0.1,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "scale_attn_by_inverse_layer_idx": false,
70
+ "scale_attn_weights": true,
71
+ "sep_token_id": null,
72
+ "summary_activation": null,
73
+ "summary_first_dropout": 0.1,
74
+ "summary_proj_to_labels": true,
75
+ "summary_type": "cls_index",
76
+ "summary_use_proj": true,
77
+ "task_specific_params": {
78
+ "text-generation": {
79
+ "do_sample": true,
80
+ "max_length": 64
81
+ }
82
+ },
83
+ "temperature": 1.0,
84
+ "tie_encoder_decoder": false,
85
+ "tie_word_embeddings": true,
86
+ "tokenizer_class": null,
87
+ "top_k": 50,
88
+ "top_p": 1.0,
89
+ "torch_dtype": null,
90
+ "torchscript": false,
91
+ "transformers_version": "4.19.0",
92
+ "typical_p": 1.0,
93
+ "use_bfloat16": false,
94
+ "use_cache": true,
95
+ "vocab_size": 50257
96
+ },
97
+ "decoder_start_token_id": 50256,
98
+ "encoder": {
99
+ "_name_or_path": "/home/Abdelrahman.Shaheen@mbzuai.ac.ae/pixel-m4",
100
+ "add_cross_attention": false,
101
+ "architectures": [
102
+ "PIXELForPreTraining"
103
+ ],
104
+ "attention_probs_dropout_prob": 0.1,
105
+ "bad_words_ids": null,
106
+ "bos_token_id": null,
107
+ "chunk_size_feed_forward": 0,
108
+ "cross_attention_hidden_size": null,
109
+ "decoder_hidden_size": 512,
110
+ "decoder_intermediate_size": 2048,
111
+ "decoder_num_attention_heads": 16,
112
+ "decoder_num_hidden_layers": 8,
113
+ "decoder_start_token_id": null,
114
+ "diversity_penalty": 0.0,
115
+ "do_eval": true,
116
+ "do_sample": false,
117
+ "early_stopping": false,
118
+ "encoder_no_repeat_ngram_size": 0,
119
+ "eos_token_id": null,
120
+ "exponential_decay_length_penalty": null,
121
+ "finetuning_task": null,
122
+ "forced_bos_token_id": null,
123
+ "forced_eos_token_id": null,
124
+ "hidden_act": "gelu",
125
+ "hidden_dropout_prob": 0.1,
126
+ "hidden_size": 768,
127
+ "id2label": {
128
+ "0": "LABEL_0",
129
+ "1": "LABEL_1"
130
+ },
131
+ "image_size": [
132
+ 16,
133
+ 8464
134
+ ],
135
+ "initializer_range": 0.02,
136
+ "intermediate_size": 3072,
137
+ "is_decoder": false,
138
+ "is_encoder_decoder": false,
139
+ "label2id": {
140
+ "LABEL_0": 0,
141
+ "LABEL_1": 1
142
+ },
143
+ "layer_norm_eps": 1e-12,
144
+ "length_penalty": 1.0,
145
+ "mask_ratio": 0.25,
146
+ "max_length": 20,
147
+ "min_length": 0,
148
+ "model_type": "pixel",
149
+ "no_repeat_ngram_size": 0,
150
+ "norm_pix_loss": true,
151
+ "num_attention_heads": 12,
152
+ "num_beam_groups": 1,
153
+ "num_beams": 1,
154
+ "num_channels": 3,
155
+ "num_hidden_layers": 12,
156
+ "num_return_sequences": 1,
157
+ "output_attentions": false,
158
+ "output_hidden_states": false,
159
+ "output_scores": false,
160
+ "pad_token_id": null,
161
+ "patch_size": 16,
162
+ "prefix": null,
163
+ "problem_type": null,
164
+ "pruned_heads": {},
165
+ "qkv_bias": true,
166
+ "remove_invalid_values": false,
167
+ "repetition_penalty": 1.0,
168
+ "return_dict": true,
169
+ "return_dict_in_generate": false,
170
+ "sep_token_id": null,
171
+ "task_specific_params": null,
172
+ "temperature": 1.0,
173
+ "tie_encoder_decoder": false,
174
+ "tie_word_embeddings": true,
175
+ "tokenizer_class": null,
176
+ "top_k": 50,
177
+ "top_p": 1.0,
178
+ "torch_dtype": "float32",
179
+ "torchscript": false,
180
+ "transformers_version": "4.19.0",
181
+ "typical_p": 1.0,
182
+ "use_bfloat16": false
183
+ },
184
+ "eos_token_id": 50256,
185
+ "is_encoder_decoder": true,
186
+ "model_type": "pixelsum",
187
+ "pad_token_id": 50256,
188
+ "tie_word_embeddings": false,
189
+ "torch_dtype": "float32",
190
+ "transformers_version": null,
191
+ "vocab_size": 50257
192
+ }
checkpoint-8600/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a636e374a9e87ac0ef19244afdb12bb41d711ee338476ff6baec22eb157eb7
3
+ size 1911148602
checkpoint-8600/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:311a1c06e1d85848cd2c4ae6d5da9e4415e15b8a5381ac9a3a8859445c6c4d29
3
+ size 980777906
checkpoint-8600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa35052d5fea61d75e933849790ce39203a5a7988c39e444f01210c0e9b54e1
3
+ size 14498
checkpoint-8600/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c02f90d2badb5b8a0ea993fb7f62f7a4f1738ca6dc9615c2e9064d72a2e02a
3
+ size 988
checkpoint-8600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:483e8dd077ac989d20fdfdbc5f6028b615391b0f7e85dab17e5b5b544a417456
3
+ size 1064
checkpoint-8600/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|pad|>"}
checkpoint-8600/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8600/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
checkpoint-8600/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff