Hugging Face's logo

Mantis-VL
/
llava_bakllava_8192

Image-Text-to-Text
Transformers
Safetensors
llava
Generated from Trainer
Inference Endpoints
Model card Files Community
DongfuJiang commited on
Commit
06d64ef
•
1 Parent(s): a092cde

Training in progress, step 1000

Browse files
Files changed (6) hide show
  1. config.json +41 -0
  2. preprocessor_config.json +45 -0
  3. special_tokens_map.json +30 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +61 -0
  6. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "llava-hf/bakLlava-v1-hf",
3
+ "architectures": [
4
+ "LlavaForConditionalGeneration"
5
+ ],
6
+ "ignore_index": -100,
7
+ "image_token_index": 32000,
8
+ "model_type": "llava",
9
+ "pad_token_id": 32001,
10
+ "projector_hidden_act": "gelu",
11
+ "text_config": {
12
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
13
+ "architectures": [
14
+ "MistralForCausalLM"
15
+ ],
16
+ "intermediate_size": 14336,
17
+ "max_position_embeddings": 32768,
18
+ "model_type": "mistral",
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-05,
21
+ "sliding_window": 4096,
22
+ "torch_dtype": "bfloat16",
23
+ "vocab_size": 32064
24
+ },
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.39.2",
27
+ "vision_config": {
28
+ "hidden_size": 1024,
29
+ "image_size": 336,
30
+ "intermediate_size": 4096,
31
+ "model_type": "clip_vision_model",
32
+ "num_attention_heads": 16,
33
+ "num_hidden_layers": 24,
34
+ "patch_size": 14,
35
+ "projection_dim": 768,
36
+ "vocab_size": 32000
37
+ },
38
+ "vision_feature_layer": -2,
39
+ "vision_feature_select_strategy": "default",
40
+ "vocab_size": 32064
41
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_center_crop",
8
+ "crop_size",
9
+ "do_rescale",
10
+ "rescale_factor",
11
+ "do_normalize",
12
+ "image_mean",
13
+ "image_std",
14
+ "do_convert_rgb",
15
+ "return_tensors",
16
+ "data_format",
17
+ "input_data_format"
18
+ ],
19
+ "crop_size": {
20
+ "height": 336,
21
+ "width": 336
22
+ },
23
+ "do_center_crop": true,
24
+ "do_convert_rgb": true,
25
+ "do_normalize": true,
26
+ "do_rescale": true,
27
+ "do_resize": true,
28
+ "image_mean": [
29
+ 0.48145466,
30
+ 0.4578275,
31
+ 0.40821073
32
+ ],
33
+ "image_processor_type": "CLIPImageProcessor",
34
+ "image_std": [
35
+ 0.26862954,
36
+ 0.26130258,
37
+ 0.27577711
38
+ ],
39
+ "processor_class": "MLlavaProcessor",
40
+ "resample": 3,
41
+ "rescale_factor": 0.00392156862745098,
42
+ "size": {
43
+ "shortest_edge": 336
44
+ }
45
+ }
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_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<image>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<pad>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [],
47
+ "bos_token": "<s>",
48
+ "clean_up_tokenization_spaces": false,
49
+ "eos_token": "</s>",
50
+ "legacy": true,
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "<pad>",
53
+ "padding_side": "left",
54
+ "processor_class": "MLlavaProcessor",
55
+ "sp_model_kwargs": {},
56
+ "spaces_between_special_tokens": false,
57
+ "tokenizer_class": "LlamaTokenizer",
58
+ "trust_remote_code": false,
59
+ "unk_token": "<unk>",
60
+ "use_default_system_prompt": true
61
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d56586e407afd7c970f0dd58b8ffb6a9be81fcf84fac9c141477f4f4a9b79e42
3
+ size 6200