Yingying11 commited on
Commit
aa7eb42
·
verified ·
1 Parent(s): e44e8dc

Add files using upload-large-folder tool

Browse files
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/training-pfs-shanghai/private/jiaqitang/project5/LLaVA-main/checkpoint_glimpse-linear-cancha-loss/llava-v1.5-7b-pretrain-glimpse-linear-cancha-loss/",
3
+ "architectures": [
4
+ "LlavaLlamaForCausalLM"
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
+ "freeze_mm_vision_resampler": false,
12
+ "freeze_vision_tower": true,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "image_aspect_ratio": "pad",
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 11008,
18
+ "max_length": 4096,
19
+ "max_position_embeddings": 4096,
20
+ "mm_hidden_size": 1024,
21
+ "mm_patch_merge_type": "flat",
22
+ "mm_projector_lr": null,
23
+ "mm_projector_type": "mlp2x_gelu",
24
+ "mm_resampler_type": null,
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": "/training-pfs-shanghai/private/jiaqitang/project5/LLaVA-main/clip-vit-large-patch14-336",
30
+ "model_type": "llava_llama",
31
+ "num_attention_heads": 32,
32
+ "num_hidden_layers": 32,
33
+ "num_key_value_heads": 32,
34
+ "pad_token_id": 0,
35
+ "pretraining_tp": 1,
36
+ "rms_norm_eps": 1e-05,
37
+ "rope_scaling": null,
38
+ "rope_theta": 10000.0,
39
+ "router_entropy_loss_coef": 0.0,
40
+ "router_entropy_loss_enabled": false,
41
+ "tie_word_embeddings": false,
42
+ "tokenizer_model_max_length": 2048,
43
+ "tokenizer_padding_side": "right",
44
+ "torch_dtype": "bfloat16",
45
+ "train_llm_layers": true,
46
+ "transformers_version": "4.37.2",
47
+ "tune_mm_mlp_adapter": false,
48
+ "tune_mm_vision_resampler": false,
49
+ "unfreeze_mm_vision_tower": false,
50
+ "use_cache": true,
51
+ "use_layerwise_vision_fusion": true,
52
+ "use_mm_proj": true,
53
+ "vision_fusion_gate_init": 0.3,
54
+ "vocab_size": 32000
55
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attn_implementation": "flash_attention_2",
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.37.2"
8
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81a0fa4cdbf8914a43c003daddfc2ed4214723b61390846d50c2cfdc050432af
3
+ size 4938985352
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b0d748996df8824693e7a55fd43f5b97c98f446c20cd690d433c8212598d69
3
+ size 4947390880
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7918cae303fd0b38ae6ea68708d2800734a7b08345166d1ea12591b6c1285232
3
+ size 4955405160
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": 2048,
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 sha256:95f591a1d7f6b191ce3115612300b3d4f51482f30eb9fc362f478626911188b5
3
+ size 7032