Hugging Face's logo

YaxinLuo
/
Gamma-MoD-Mini-Gemini-HD-7b-0.34

Safetensors
mod_mgm
Model card Files Community
YaxinLuo commited on
Commit
ff2c743
•
1 Parent(s): 0f3e7ca

Upload 10 files

Browse files
Files changed (10) hide show
  1. config.json +87 -0
  2. model-00001-of-00003.safetensors +3 -0
  3. model-00002-of-00003.safetensors +3 -0
  4. model-00003-of-00003.safetensors +3 -0
  5. model.safetensors.index.json +0 -0
  6. special_tokens_map.json +24 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +42 -0
  9. trainer_state.json +0 -0
  10. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/vicuna/vicuna-7b-v1.5",
3
+ "architectures": [
4
+ "MoDMGMLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "freeze_mm_mlp_adapter": false,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "image_aspect_ratio": "pad",
14
+ "image_global": true,
15
+ "image_grid": 2,
16
+ "image_grid_pinpoints": null,
17
+ "image_size_aux": 1536,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 11008,
20
+ "max_position_embeddings": 4096,
21
+ "mm_hidden_size": 1024,
22
+ "mm_hidden_size_aux": 2880,
23
+ "mm_projector_lr": null,
24
+ "mm_projector_type": "mlp2x_gelu",
25
+ "mm_use_im_patch_token": false,
26
+ "mm_use_im_start_end": false,
27
+ "mm_vision_select_feature": "patch",
28
+ "mm_vision_select_layer": -2,
29
+ "mm_vision_tower": "model_zoo/OpenAI/clip-vit-large-patch14-336",
30
+ "mm_vision_tower_aux": "model_zoo/OpenAI/openclip-convnext-large-d-320-laion2B-s29B-b131K-ft-soup",
31
+ "mod": {
32
+ "capacity_factor": 0.5,
33
+ "mod_enable": true,
34
+ "mod_layers_idx": [
35
+ 3,
36
+ 4,
37
+ 5,
38
+ 6,
39
+ 7,
40
+ 8,
41
+ 9,
42
+ 10,
43
+ 11,
44
+ 12,
45
+ 13,
46
+ 14,
47
+ 15,
48
+ 16,
49
+ 17,
50
+ 18,
51
+ 19,
52
+ 20,
53
+ 21,
54
+ 22,
55
+ 23,
56
+ 24,
57
+ 25,
58
+ 26,
59
+ 27,
60
+ 28,
61
+ 29,
62
+ 30
63
+ ],
64
+ "mod_mode": "arank_mod",
65
+ "router_aux_loss_coef": 0.01
66
+ },
67
+ "model_type": "mod_mgm",
68
+ "num_attention_heads": 32,
69
+ "num_hidden_layers": 32,
70
+ "num_key_value_heads": 32,
71
+ "optimize_vision_tower": false,
72
+ "optimize_vision_tower_aux": false,
73
+ "pad_token_id": 0,
74
+ "pretraining_tp": 1,
75
+ "rms_norm_eps": 1e-05,
76
+ "rope_scaling": null,
77
+ "rope_theta": 10000.0,
78
+ "tie_word_embeddings": false,
79
+ "tokenizer_model_max_length": 4096,
80
+ "tokenizer_padding_side": "right",
81
+ "torch_dtype": "bfloat16",
82
+ "transformers_version": "4.36.2",
83
+ "tune_mm_mlp_adapter": false,
84
+ "use_cache": true,
85
+ "use_mm_proj": true,
86
+ "vocab_size": 32000
87
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581d7730defd3147b8696cd80520f12401980ca5e185a7b27a31546de535fcd2
3
+ size 4939001840
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97301aa9483b2970d5f25d1218c9158219032a5de2aaff70ad76ddcfc64b71c4
3
+ size 4947390880
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39132ae16e9ce662068019511bf82ea5ba4242fe6b999ae37fc20423856d66ce
3
+ size 4645953464
model.safetensors.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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 4096,
35
+ "pad_token": "<unk>",
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
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 sha256:7f430135661d64a6d1e15b443527f1a62f35efae2b4a6bfba35ca599fe43532c
3
+ size 6331