Dongfu Jiang commited on
Commit
50cbce3
1 Parent(s): 86be537

Training in progress, step 500

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MFuyu/mfuyu_llava_8192_480p",
3
+ "architectures": [
4
+ "MFuyuForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 71013,
9
+ "hidden_act": "relu2",
10
+ "hidden_dropout": 0.0,
11
+ "hidden_size": 4096,
12
+ "image_size": 300,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 16384,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 16384,
17
+ "model_type": "fuyu",
18
+ "num_attention_heads": 64,
19
+ "num_channels": 3,
20
+ "num_hidden_layers": 36,
21
+ "partial_rotary_factor": 0.5,
22
+ "patch_size": 30,
23
+ "qk_layernorm": true,
24
+ "rope_scaling": null,
25
+ "rope_theta": 25000.0,
26
+ "text_config": {
27
+ "model_type": "persimmon",
28
+ "vocab_size": 262146
29
+ },
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.37.0",
33
+ "use_cache": true,
34
+ "vocab_size": 262146
35
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_pad": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": 0.5,
7
+ "image_processor_type": "FuyuImageProcessor",
8
+ "image_std": 0.5,
9
+ "padding_mode": "constant",
10
+ "padding_value": 1.0,
11
+ "patch_size": {
12
+ "height": 30,
13
+ "width": 30
14
+ },
15
+ "processor_class": "MFuyuProcessor",
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 480,
20
+ "width": 660
21
+ },
22
+ "target_height": 1080,
23
+ "target_width": 1920
24
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "|IMAGE|",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "|ENDOFIMAGE|",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "|ENDOFTEXT|",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "|ENDOFTEXT|",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "<unk>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6db0b2169918176bbed18b26e73d12d8c09dfa0ed8b248d2c054e7df9f5cfce
3
+ size 16454942
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "71013": {
14
+ "content": "|ENDOFTEXT|",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "262144": {
22
+ "content": "|IMAGE|",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "262145": {
30
+ "content": "|ENDOFIMAGE|",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "additional_special_tokens": [
39
+ "|IMAGE|",
40
+ "|ENDOFIMAGE|"
41
+ ],
42
+ "bos_token": "|ENDOFTEXT|",
43
+ "clean_up_tokenization_spaces": false,
44
+ "eos_token": "|ENDOFTEXT|",
45
+ "legacy": true,
46
+ "model_max_length": 1000000000000000019884624838656,
47
+ "pad_token": null,
48
+ "processor_class": "MFuyuProcessor",
49
+ "sp_model_kwargs": {},
50
+ "spaces_between_special_tokens": false,
51
+ "tokenizer_class": "LlamaTokenizer",
52
+ "unk_token": "<unk>",
53
+ "use_default_system_prompt": true
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:866b4502943c5c5b36f78b57b1f97afe5d28ac43b32fb5fcf21f0304292de662
3
+ size 6008