rasoulasadianub commited on
Commit
fd01d82
·
verified ·
1 Parent(s): 975a15d

Initial model upload

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[N]": 42000
3
+ }
config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VisionEncoderDecoderModel"
4
+ ],
5
+ "bos_token_id": 5,
6
+ "decoder": {
7
+ "_name_or_path": "weights/gpt2",
8
+ "activation_function": "gelu_new",
9
+ "add_cross_attention": true,
10
+ "architectures": [
11
+ "GPT2Model"
12
+ ],
13
+ "attn_pdrop": 0.1,
14
+ "bos_token_id": 5,
15
+ "embd_pdrop": 0.1,
16
+ "eos_token_id": 5,
17
+ "gradient_checkpointing": false,
18
+ "initializer_range": 0.02,
19
+ "is_decoder": true,
20
+ "layer_norm_epsilon": 1e-05,
21
+ "max_length": 50,
22
+ "model_type": "gpt2",
23
+ "n_ctx": 1024,
24
+ "n_embd": 768,
25
+ "n_head": 12,
26
+ "n_inner": null,
27
+ "n_layer": 12,
28
+ "n_positions": 1024,
29
+ "reorder_and_upcast_attn": false,
30
+ "resid_pdrop": 0.1,
31
+ "scale_attn_by_inverse_layer_idx": false,
32
+ "scale_attn_weights": true,
33
+ "summary_activation": null,
34
+ "summary_first_dropout": 0.1,
35
+ "summary_proj_to_labels": true,
36
+ "summary_type": "cls_index",
37
+ "summary_use_proj": true,
38
+ "task_specific_params": {
39
+ "text-generation": {
40
+ "do_sample": true,
41
+ "max_length": 50,
42
+ "top_k": 50,
43
+ "top_p": 0.95
44
+ }
45
+ },
46
+ "torch_dtype": "float32",
47
+ "use_cache": true,
48
+ "vocab_size": 42001
49
+ },
50
+ "decoder_start_token_id": 5,
51
+ "encoder": {
52
+ "_name_or_path": "weights/dinov2-base",
53
+ "apply_layernorm": true,
54
+ "architectures": [
55
+ "Dinov2Model"
56
+ ],
57
+ "attention_probs_dropout_prob": 0.0,
58
+ "drop_path_rate": 0.0,
59
+ "hidden_act": "gelu",
60
+ "hidden_dropout_prob": 0.0,
61
+ "hidden_size": 768,
62
+ "image_size": 518,
63
+ "initializer_range": 0.02,
64
+ "layer_norm_eps": 1e-06,
65
+ "layerscale_value": 1.0,
66
+ "mlp_ratio": 4,
67
+ "model_type": "dinov2",
68
+ "num_attention_heads": 12,
69
+ "num_channels": 3,
70
+ "num_hidden_layers": 12,
71
+ "out_features": [
72
+ "stage12"
73
+ ],
74
+ "out_indices": [
75
+ 12
76
+ ],
77
+ "patch_size": 14,
78
+ "qkv_bias": true,
79
+ "reshape_hidden_states": true,
80
+ "stage_names": [
81
+ "stem",
82
+ "stage1",
83
+ "stage2",
84
+ "stage3",
85
+ "stage4",
86
+ "stage5",
87
+ "stage6",
88
+ "stage7",
89
+ "stage8",
90
+ "stage9",
91
+ "stage10",
92
+ "stage11",
93
+ "stage12"
94
+ ],
95
+ "torch_dtype": "float32",
96
+ "use_mask_token": true,
97
+ "use_swiglu_ffn": false
98
+ },
99
+ "eos_token_id": 5,
100
+ "is_encoder_decoder": true,
101
+ "model_type": "vision-encoder-decoder",
102
+ "pad_token_id": 5,
103
+ "tie_word_embeddings": false,
104
+ "torch_dtype": "float32",
105
+ "transformers_version": "4.55.2",
106
+ "vocab_size": 42001
107
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 5,
4
+ "eos_token_id": 5,
5
+ "max_length": 50,
6
+ "num_beams": 3,
7
+ "pad_token_id": 5,
8
+ "transformers_version": "4.55.2"
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b29f63ea8b6734ee7042aef6fdc7cf89451c02d7c9959d079974546db4c9b4
3
+ size 932239776
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<|endoftext|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<|startoftext|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<nl>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<hs>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<sep>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<cls>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "42000": {
93
+ "content": "[N]",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ }
100
+ },
101
+ "bos_token": "<|endoftext|>",
102
+ "clean_up_tokenization_spaces": false,
103
+ "eos_token": "<|endoftext|>",
104
+ "errors": "replace",
105
+ "extra_special_tokens": {},
106
+ "model_max_length": 1024,
107
+ "pad_token": "<|endoftext|>",
108
+ "tokenizer_class": "GPT2Tokenizer",
109
+ "unk_token": "<|endoftext|>"
110
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff