Hugging Face's logo

RISys-Lab
/
sparrow-finetune

PyTorch
VideoGPT+
custom_code
Model card Files
xet
 Community
1
MohamadAlansari commited on
Commit
3a993a6
·
verified ·
1 Parent(s): 9f4fdb4

Upload 11 files

Browse files
Files changed (11) hide show
  1. added_tokens.json +15 -0
  2. config (copy).json +72 -0
  3. config.json +72 -0
  4. generation_config.json +12 -0
  5. pytorch_model-00001-of-00003.bin +3 -0
  6. pytorch_model-00002-of-00003.bin +3 -0
  7. pytorch_model-00003-of-00003.bin +3 -0
  8. pytorch_model.bin.index.json +0 -0
  9. special_tokens_map.json +24 -0
  10. tokenizer.model +3 -0
  11. tokenizer_config.json +148 -0
added_tokens.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010,
13
+ "[BOX]": 32012,
14
+ "[SEG]": 32011
15
+ }
config (copy).json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/media/ansari/b31f34fc-bbc3-4980-81cb-193d5242a2c6/mnt/Sparrow/VideoGLaMM/VideoGLaMM/VideoGLaMM/checkpoints/VideoGPTPlus-Phi3-SAM2-8frame-tunevlproj-epoch29",
3
+ "architectures": [
4
+ "SPARROWForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
11
+ },
12
+ "bos_token_id": 1,
13
+ "box_token_idx": 32012,
14
+ "config": {
15
+ "freeze": false,
16
+ "mm_tune": true,
17
+ "vision_tune": false
18
+ },
19
+ "embd_pdrop": 0.0,
20
+ "eos_token_id": 32000,
21
+ "freeze_mm_mlp_adapter": false,
22
+ "hidden_act": "silu",
23
+ "hidden_size": 3072,
24
+ "image_aspect_ratio": "square",
25
+ "image_grid_pinpoints": null,
26
+ "image_mm_hidden_size": 1024,
27
+ "image_mm_projector_type": "mlp2x_gelu",
28
+ "image_mm_vision_tower": "openai/clip-vit-large-patch14-336",
29
+ "image_vision_tower": "openai/clip-vit-large-patch14-336",
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 8192,
32
+ "mask_decoder_itm": false,
33
+ "max_position_embeddings": 4096,
34
+ "mlp_bias": false,
35
+ "mm_hidden_size": 1408,
36
+ "mm_projector_lr": 2e-05,
37
+ "mm_projector_type": "mlp2x_gelu",
38
+ "mm_use_box_start_end": false,
39
+ "mm_use_im_patch_token": false,
40
+ "mm_use_im_start_end": false,
41
+ "mm_vision_select_feature": "patch",
42
+ "mm_vision_select_layer": -2,
43
+ "mm_vision_tower": "OpenGVLab/InternVideo2-Stage2_1B-224p-f4/InternVideo2-stage2_1b-224p-f4.pt",
44
+ "model_type": "VideoGPT+",
45
+ "num_attention_heads": 32,
46
+ "num_hidden_layers": 32,
47
+ "num_key_value_heads": 32,
48
+ "original_max_position_embeddings": 4096,
49
+ "out_dim": 256,
50
+ "pad_token_id": 0,
51
+ "pretrain_image_mm_mlp_adapter": null,
52
+ "pretrain_mm_mlp_adapter": null,
53
+ "pretraining_tp": 1,
54
+ "resid_pdrop": 0.0,
55
+ "rms_norm_eps": 1e-05,
56
+ "rope_scaling": null,
57
+ "rope_theta": 10000.0,
58
+ "s2": false,
59
+ "s2_scales": "336,672,1008",
60
+ "seg_token_idx": 32011,
61
+ "sliding_window": 2048,
62
+ "tie_word_embeddings": false,
63
+ "torch_dtype": "float16",
64
+ "train_mask_decoder": false,
65
+ "transformers_version": "4.41.0",
66
+ "tune_mm_mlp_adapter": false,
67
+ "use_cache": false,
68
+ "use_mm_proj": true,
69
+ "use_sam2": true,
70
+ "vision_tower": "OpenGVLab/InternVideo2-Stage2_1B-224p-f4/InternVideo2-stage2_1b-224p-f4.pt",
71
+ "vocab_size": 32013
72
+ }
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "checkpoints/VideoGPTPlus-Phi3-SAM2-8frame-tunevlproj-epoch29",
3
+ "architectures": [
4
+ "SPARROWForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
11
+ },
12
+ "bos_token_id": 1,
13
+ "box_token_idx": 32012,
14
+ "config": {
15
+ "freeze": false,
16
+ "mm_tune": true,
17
+ "vision_tune": false
18
+ },
19
+ "embd_pdrop": 0.0,
20
+ "eos_token_id": 32000,
21
+ "freeze_mm_mlp_adapter": false,
22
+ "hidden_act": "silu",
23
+ "hidden_size": 3072,
24
+ "image_aspect_ratio": "square",
25
+ "image_grid_pinpoints": null,
26
+ "image_mm_hidden_size": 1024,
27
+ "image_mm_projector_type": "mlp2x_gelu",
28
+ "image_mm_vision_tower": "openai/clip-vit-large-patch14-336",
29
+ "image_vision_tower": "openai/clip-vit-large-patch14-336",
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 8192,
32
+ "mask_decoder_itm": false,
33
+ "max_position_embeddings": 4096,
34
+ "mlp_bias": false,
35
+ "mm_hidden_size": 1408,
36
+ "mm_projector_lr": 2e-05,
37
+ "mm_projector_type": "mlp2x_gelu",
38
+ "mm_use_box_start_end": false,
39
+ "mm_use_im_patch_token": false,
40
+ "mm_use_im_start_end": false,
41
+ "mm_vision_select_feature": "patch",
42
+ "mm_vision_select_layer": -2,
43
+ "mm_vision_tower": "OpenGVLab/InternVideo2-Stage2_1B-224p-f4/InternVideo2-stage2_1b-224p-f4.pt",
44
+ "model_type": "VideoGPT+",
45
+ "num_attention_heads": 32,
46
+ "num_hidden_layers": 32,
47
+ "num_key_value_heads": 32,
48
+ "original_max_position_embeddings": 4096,
49
+ "out_dim": 256,
50
+ "pad_token_id": 0,
51
+ "pretrain_image_mm_mlp_adapter": null,
52
+ "pretrain_mm_mlp_adapter": null,
53
+ "pretraining_tp": 1,
54
+ "resid_pdrop": 0.0,
55
+ "rms_norm_eps": 1e-05,
56
+ "rope_scaling": null,
57
+ "rope_theta": 10000.0,
58
+ "s2": false,
59
+ "s2_scales": "336,672,1008",
60
+ "seg_token_idx": 32011,
61
+ "sliding_window": 2048,
62
+ "tie_word_embeddings": false,
63
+ "torch_dtype": "float16",
64
+ "train_mask_decoder": false,
65
+ "transformers_version": "4.41.0",
66
+ "tune_mm_mlp_adapter": false,
67
+ "use_cache": false,
68
+ "use_mm_proj": true,
69
+ "use_sam2": true,
70
+ "vision_tower": "OpenGVLab/InternVideo2-Stage2_1B-224p-f4/InternVideo2-stage2_1b-224p-f4.pt",
71
+ "vocab_size": 32013
72
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 32000,
7
+ 32001,
8
+ 32007
9
+ ],
10
+ "pad_token_id": 32000,
11
+ "transformers_version": "4.41.0"
12
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1286a9979486647921612275ebcd559a1b8bf596a0005d94fa0acaef7003356d
3
+ size 4980069137
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4ef8066b4a5ce2ad822bb3c40980935ac59faadb94756d5c8d1ac2d1f1817a
3
+ size 4996054198
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d4a6de7ac7005a368a4ef733880b7ec4cc11656f48591d574e6d2dabf22b93c
3
+ size 294952919
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
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": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32011": {
119
+ "content": "[SEG]",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "32012": {
127
+ "content": "[BOX]",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ }
134
+ },
135
+ "bos_token": "<s>",
136
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
137
+ "clean_up_tokenization_spaces": false,
138
+ "eos_token": "<|endoftext|>",
139
+ "legacy": false,
140
+ "model_max_length": 4096,
141
+ "pad_token": "<unk>",
142
+ "padding_side": "left",
143
+ "sp_model_kwargs": {},
144
+ "spaces_between_special_tokens": false,
145
+ "tokenizer_class": "LlamaTokenizer",
146
+ "unk_token": "<unk>",
147
+ "use_default_system_prompt": false
148
+ }