DongfuJiang commited on
Commit
ae10415
1 Parent(s): e10347e

Training in progress, step 500

Browse files
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "llava-hf/llava-v1.6-mistral-7b-hf",
3
+ "architectures": [
4
+ "LlavaNextForConditionalGeneration"
5
+ ],
6
+ "ignore_index": -100,
7
+ "image_grid_pinpoints": [
8
+ [
9
+ 336,
10
+ 672
11
+ ],
12
+ [
13
+ 672,
14
+ 336
15
+ ],
16
+ [
17
+ 672,
18
+ 672
19
+ ],
20
+ [
21
+ 1008,
22
+ 336
23
+ ],
24
+ [
25
+ 336,
26
+ 1008
27
+ ]
28
+ ],
29
+ "image_token_index": 32000,
30
+ "model_type": "llava_next",
31
+ "projector_hidden_act": "gelu",
32
+ "text_config": {
33
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
34
+ "architectures": [
35
+ "MistralForCausalLM"
36
+ ],
37
+ "intermediate_size": 14336,
38
+ "max_position_embeddings": 32768,
39
+ "model_type": "mistral",
40
+ "num_key_value_heads": 8,
41
+ "rms_norm_eps": 1e-05,
42
+ "rope_theta": 1000000.0,
43
+ "sliding_window": null,
44
+ "torch_dtype": "bfloat16",
45
+ "vocab_size": 32064
46
+ },
47
+ "torch_dtype": "bfloat16",
48
+ "transformers_version": "4.39.2",
49
+ "use_image_newline_parameter": true,
50
+ "vision_config": {
51
+ "hidden_size": 1024,
52
+ "image_size": 336,
53
+ "intermediate_size": 4096,
54
+ "model_type": "clip_vision_model",
55
+ "num_attention_heads": 16,
56
+ "num_hidden_layers": 24,
57
+ "patch_size": 14,
58
+ "projection_dim": 768,
59
+ "vocab_size": 32000
60
+ },
61
+ "vision_feature_layer": -2,
62
+ "vision_feature_select_strategy": "default",
63
+ "vocab_size": 32064
64
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "aspect_ratio_setting": "anyres",
3
+ "crop_size": {
4
+ "height": 336,
5
+ "width": 336
6
+ },
7
+ "do_center_crop": true,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "image_grid_pinpoints": [
13
+ [
14
+ 336,
15
+ 672
16
+ ],
17
+ [
18
+ 672,
19
+ 336
20
+ ],
21
+ [
22
+ 672,
23
+ 672
24
+ ],
25
+ [
26
+ 1008,
27
+ 336
28
+ ],
29
+ [
30
+ 336,
31
+ 1008
32
+ ]
33
+ ],
34
+ "image_mean": [
35
+ 0.48145466,
36
+ 0.4578275,
37
+ 0.40821073
38
+ ],
39
+ "image_processor_type": "LlavaNextImageProcessor",
40
+ "image_std": [
41
+ 0.26862954,
42
+ 0.26130258,
43
+ 0.27577711
44
+ ],
45
+ "processor_class": "MLlavaNextProcessor",
46
+ "resample": 3,
47
+ "rescale_factor": 0.00392156862745098,
48
+ "size": {
49
+ "shortest_edge": 336
50
+ }
51
+ }
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 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
49
+ "clean_up_tokenization_spaces": false,
50
+ "eos_token": "</s>",
51
+ "legacy": true,
52
+ "max_length": null,
53
+ "model_max_length": 1000000000000000019884624838656,
54
+ "pad_to_multiple_of": null,
55
+ "pad_token": "<pad>",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "left",
58
+ "processor_class": "MLlavaNextProcessor",
59
+ "sp_model_kwargs": {},
60
+ "spaces_between_special_tokens": false,
61
+ "tokenizer_class": "LlamaTokenizer",
62
+ "unk_token": "<unk>",
63
+ "use_default_system_prompt": false
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b4ff2590195badbca6db725cbe084461b9b829eb7ccf53b6cb20a3336c60e0
3
+ size 6200