YanweiLi commited on
Commit
6b4e8b7
1 Parent(s): 71fa556

First model version

Browse files
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "model_zoo/LLM/vicuna/13B-V1.5",
3
+ "architectures": [
4
+ "LlavaLlamaUniForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "aux_img_fold": false,
9
+ "aux_with_fpn": false,
10
+ "bos_token_id": 1,
11
+ "eos_token_id": 2,
12
+ "freeze_mm_mlp_adapter": false,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 5120,
15
+ "image_aspect_ratio": "pad",
16
+ "image_global": true,
17
+ "image_grid": 2,
18
+ "image_grid_pinpoints": null,
19
+ "image_size_aux": 1536,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 13824,
22
+ "max_length": 4096,
23
+ "max_position_embeddings": 4096,
24
+ "mm_hidden_size": 1024,
25
+ "mm_hidden_size_aux": 2880,
26
+ "mm_projector_lr": null,
27
+ "mm_projector_type": "mlp2x_gelu",
28
+ "mm_use_im_patch_token": false,
29
+ "mm_use_im_start_end": false,
30
+ "mm_vision_select_feature": "patch",
31
+ "mm_vision_select_layer": -2,
32
+ "mm_vision_tower": "model_zoo/OpenAI/clip-vit-large-patch14-336",
33
+ "mm_vision_tower_aux": "model_zoo/OpenAI/openclip-convnext-large-d-320-laion2B-s29B-b131K-ft-soup",
34
+ "model_type": "llava_uni",
35
+ "num_attention_heads": 40,
36
+ "num_hidden_layers": 40,
37
+ "num_key_value_heads": 40,
38
+ "optimize_vision_tower": false,
39
+ "optimize_vision_tower_aux": false,
40
+ "pad_token_id": 0,
41
+ "pretraining_tp": 1,
42
+ "rms_norm_eps": 1e-05,
43
+ "rope_scaling": null,
44
+ "rope_theta": 10000.0,
45
+ "tie_word_embeddings": false,
46
+ "tokenizer_model_max_length": 4096,
47
+ "tokenizer_padding_side": "right",
48
+ "torch_dtype": "bfloat16",
49
+ "transformers_version": "4.36.2",
50
+ "tune_mm_mlp_adapter": false,
51
+ "unified_resampler": "simple_sum",
52
+ "use_cache": true,
53
+ "use_mm_proj": true,
54
+ "use_same_im_pos": false,
55
+ "video_grid": -1,
56
+ "vocab_size": 32000
57
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d38d677229e08e0ee2975896eab709087c881846d1bb14278677a713d000bbb
3
+ size 4978265800
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9df7ba5b5e51b0e3f51067311c290dae84afc124c1f6c9133ee94988d94d0b1
3
+ size 4970422232
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82b940e837ec62b85510d20db5688886ce0392bad1a4eb532b7f25eeaa9df7ff
3
+ size 4970422256
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:338755c249ca95310491a001eeadf32aadfa631b06649d354efe3d316535af20
3
+ size 4933701504
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386d0202e07b3ab15bed817b2e18f2d96d991543c890b107497fda705d97ee19
3
+ size 4933722216
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53c9ba9e423057fc3e598248b282ee7f5c2e75b0e1f8f8d15a8adc6fc053ba6
3
+ size 2321677176
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:ac79d73401418cc8bdf2a8f12262d6b8b3e3dd8b6112469381f73c0c990d0f16
3
+ size 5883