Hugging Face's logo

YaxinLuo
/
Gamma-MoD-llava-hr-13b-0.34

PyTorch
English
mod_llava_llama
Model card Files Community
YaxinLuo commited on
Commit
fddf168
•
1 Parent(s): 4d28665

Upload 11 files

Browse files
Files changed (11) hide show
  1. config.json +88 -0
  2. generation_config.json +10 -0
  3. pytorch_model-00001-of-00003.bin +3 -0
  4. pytorch_model-00002-of-00003.bin +3 -0
  5. pytorch_model-00003-of-00003.bin +3 -0
  6. pytorch_model.bin.index.json +0 -0
  7. special_tokens_map.json +24 -0
  8. tokenizer.model +3 -0
  9. tokenizer_config.json +35 -0
  10. trainer_state.json +0 -0
  11. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/vicuna/vicuna-13b-v1.5",
3
+ "architectures": [
4
+ "MoDLLaVALlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "delay_load": false,
8
+ "eos_token_id": 2,
9
+ "freeze_mm_mlp_adapter": false,
10
+ "freeze_vision": false,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 5120,
13
+ "image_aspect_ratio": "pad",
14
+ "image_grid_pinpoints": null,
15
+ "initializer_range": 0.02,
16
+ "input_image_size": 1024,
17
+ "intermediate_size": 13824,
18
+ "is_multipath_encoder": true,
19
+ "max_length": 4096,
20
+ "max_position_embeddings": 4096,
21
+ "mm_hidden_size": 1024,
22
+ "mm_projector_type": "mlp2x_gelu",
23
+ "mm_use_im_patch_token": false,
24
+ "mm_use_im_start_end": false,
25
+ "mm_vision_select_feature": "patch",
26
+ "mm_vision_select_layer": -2,
27
+ "mm_vision_tower": "openai/clip-vit-large-patch14-336",
28
+ "mod": {
29
+ "capacity_factor": 0.5,
30
+ "mod_enable": true,
31
+ "mod_layers_idx": [
32
+ 3,
33
+ 4,
34
+ 5,
35
+ 6,
36
+ 7,
37
+ 8,
38
+ 9,
39
+ 10,
40
+ 11,
41
+ 12,
42
+ 13,
43
+ 14,
44
+ 15,
45
+ 16,
46
+ 17,
47
+ 18,
48
+ 19,
49
+ 20,
50
+ 21,
51
+ 22,
52
+ 23,
53
+ 24,
54
+ 25,
55
+ 26,
56
+ 27,
57
+ 28,
58
+ 29,
59
+ 30,
60
+ 31,
61
+ 32,
62
+ 33,
63
+ 34,
64
+ 35,
65
+ 36,
66
+ 37,
67
+ 38
68
+ ],
69
+ "mod_mode": "arank_mod",
70
+ "router_aux_loss_coef": 0.01
71
+ },
72
+ "model_type": "mod_llava_llama",
73
+ "num_attention_heads": 40,
74
+ "num_hidden_layers": 40,
75
+ "num_key_value_heads": 40,
76
+ "pad_token_id": 0,
77
+ "pretraining_tp": 1,
78
+ "rms_norm_eps": 1e-05,
79
+ "rope_scaling": null,
80
+ "tie_word_embeddings": false,
81
+ "torch_dtype": "bfloat16",
82
+ "transformers_version": "4.31.0",
83
+ "tune_mm_mlp_adapter": false,
84
+ "use_cache": true,
85
+ "use_mm_proj": true,
86
+ "vision_tower_slow": "convnext_large_mlp.clip_laion2b_ft_320",
87
+ "vocab_size": 32000
88
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.9,
8
+ "top_p": 0.6,
9
+ "transformers_version": "4.31.0"
10
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c394c1c54b862cc72426aacce469148424d3d9798182d821ba29e844c9cf1b6
3
+ size 9948749352
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11d05e58ba249f8f03fa9d98edb917943f811a95847d57bb6346bb4255e1fb30
3
+ size 9904163463
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a28dffc2cf7875fe50df3e1368e736ec937859c9689e5dcfc55c705be10d1818
3
+ size 7291251922
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": "</s>",
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 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 2496,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d39e0ef9ba692eedd40611279da510e363bfde0ee4c44a5b1447c2613fed2893
3
+ size 6584