Hugging Face's logo

Mantis-VL
/
videollava-7b-video-eval-50k_2048

Transformers
Safetensors
video_llava
pretraining
Generated from Trainer
Inference Endpoints
Model card Files Community
hexuan21 commited on
Commit
b1867d3
•
1 Parent(s): a427b28

Training in progress, step 50

Browse files
Files changed (8) hide show
  1. added_tokens.json +5 -0
  2. config.json +39 -0
  3. preprocessor_config.json +46 -0
  4. special_tokens_map.json +30 -0
  5. tokenizer.json +0 -0
  6. tokenizer.model +3 -0
  7. tokenizer_config.json +68 -0
  8. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<image>": 32000,
3
+ "<pad>": 32002,
4
+ "<video>": 32001
5
+ }
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "LanguageBind/Video-LLaVA-7B-hf",
3
+ "architectures": [
4
+ "VideoLlavaForConditionalGeneration"
5
+ ],
6
+ "ignore_index": -100,
7
+ "image_token_index": 32000,
8
+ "model_type": "video_llava",
9
+ "pad_token_id": 32002,
10
+ "projector_hidden_act": "gelu",
11
+ "text_config": {
12
+ "_name_or_path": "lmsys/vicuna-7b-v1.5",
13
+ "architectures": [
14
+ "LlamaForCausalLM"
15
+ ],
16
+ "max_position_embeddings": 4096,
17
+ "model_type": "llama",
18
+ "pad_token_id": 0,
19
+ "rms_norm_eps": 1e-05,
20
+ "torch_dtype": "float16",
21
+ "vocab_size": 32064
22
+ },
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.41.1",
25
+ "video_token_index": 32001,
26
+ "vision_config": {
27
+ "hidden_size": 1024,
28
+ "intermediate_size": 4096,
29
+ "model_type": "clip_vision_model",
30
+ "num_attention_heads": 16,
31
+ "num_hidden_layers": 24,
32
+ "patch_size": 14,
33
+ "projection_dim": 768,
34
+ "vocab_size": 32000
35
+ },
36
+ "vision_feature_layer": -2,
37
+ "vision_feature_select_strategy": "default",
38
+ "vocab_size": 32064
39
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "videos",
5
+ "do_resize",
6
+ "size",
7
+ "resample",
8
+ "do_center_crop",
9
+ "crop_size",
10
+ "do_rescale",
11
+ "rescale_factor",
12
+ "do_normalize",
13
+ "image_mean",
14
+ "image_std",
15
+ "do_convert_rgb",
16
+ "return_tensors",
17
+ "data_format",
18
+ "input_data_format"
19
+ ],
20
+ "crop_size": {
21
+ "height": 224,
22
+ "width": 224
23
+ },
24
+ "do_center_crop": true,
25
+ "do_convert_rgb": true,
26
+ "do_normalize": true,
27
+ "do_rescale": true,
28
+ "do_resize": true,
29
+ "image_mean": [
30
+ 0.48145466,
31
+ 0.4578275,
32
+ 0.40821073
33
+ ],
34
+ "image_processor_type": "VideoLlavaImageProcessor",
35
+ "image_std": [
36
+ 0.26862954,
37
+ 0.26130258,
38
+ 0.27577711
39
+ ],
40
+ "processor_class": "VideoLlavaProcessor",
41
+ "resample": 3,
42
+ "rescale_factor": 0.00392156862745098,
43
+ "size": {
44
+ "shortest_edge": 224
45
+ }
46
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
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": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<image>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<video>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<pad>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ }
54
+ },
55
+ "bos_token": "<s>",
56
+ "clean_up_tokenization_spaces": false,
57
+ "eos_token": "</s>",
58
+ "legacy": false,
59
+ "model_max_length": 4096,
60
+ "pad_token": "<pad>",
61
+ "padding_side": "left",
62
+ "processor_class": "VideoLlavaProcessor",
63
+ "sp_model_kwargs": {},
64
+ "spaces_between_special_tokens": false,
65
+ "tokenizer_class": "LlamaTokenizer",
66
+ "unk_token": "<unk>",
67
+ "use_default_system_prompt": false
68
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f024aa529903c8b4ebb3764a4173f42ebd4256737ba468b37dbe1fee50a03b23
3
+ size 6456