ziqingyang commited on
Commit
295103f
1 Parent(s): 70445c2

Upload 8 files

Browse files
adapter_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": null,
3
+ "bias": "none",
4
+ "enable_lora": null,
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "lora_alpha": 32,
8
+ "lora_dropout": 0.1,
9
+ "merge_weights": false,
10
+ "modules_to_save": [
11
+ "image_projection_layer",
12
+ "embed_tokens",
13
+ "lm_head",
14
+ "visual_resampler"
15
+ ],
16
+ "peft_type": "LORA",
17
+ "r": 8,
18
+ "target_modules": ".*(vision_model|text_model).*(self_attn|mlp).*(q_proj|k_proj|v_proj|o_proj|out_proj|fc1|fc2|gate_proj|down_proj|up_proj)$",
19
+ "task_type": "CAUSAL_LM"
20
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c70c9fdc2f462a138b6739ae963bc1cd16515363363307927ff0eda16e7176d
3
+ size 1027494823
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</img>": 49955,
3
+ "<img>": 49954,
4
+ "<img_token>": 49957,
5
+ "<pad>": 49956
6
+ }
config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vision_config": {
3
+ "_name_or_path": "",
4
+ "add_cross_attention": false,
5
+ "architectures": null,
6
+ "attention_dropout": 0.0,
7
+ "bad_words_ids": null,
8
+ "bos_token_id": null,
9
+ "chunk_size_feed_forward": 0,
10
+ "cross_attention_hidden_size": null,
11
+ "decoder_start_token_id": null,
12
+ "diversity_penalty": 0.0,
13
+ "do_sample": false,
14
+ "dropout": 0.0,
15
+ "early_stopping": false,
16
+ "encoder_no_repeat_ngram_size": 0,
17
+ "eos_token_id": null,
18
+ "finetuning_task": null,
19
+ "forced_bos_token_id": null,
20
+ "forced_eos_token_id": null,
21
+ "hidden_act": "quick_gelu",
22
+ "hidden_size": 1024,
23
+ "id2label": {
24
+ "0": "LABEL_0",
25
+ "1": "LABEL_1"
26
+ },
27
+ "image_size": 224,
28
+ "initializer_factor": 1.0,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 4096,
31
+ "is_decoder": false,
32
+ "is_encoder_decoder": false,
33
+ "label2id": {
34
+ "LABEL_0": 0,
35
+ "LABEL_1": 1
36
+ },
37
+ "layer_norm_eps": 1e-05,
38
+ "length_penalty": 1.0,
39
+ "max_length": 20,
40
+ "min_length": 0,
41
+ "model_type": "clip_vision_model",
42
+ "no_repeat_ngram_size": 0,
43
+ "num_attention_heads": 16,
44
+ "num_beam_groups": 1,
45
+ "num_beams": 1,
46
+ "num_hidden_layers": 24,
47
+ "num_return_sequences": 1,
48
+ "output_attentions": false,
49
+ "output_hidden_states": false,
50
+ "output_scores": false,
51
+ "pad_token_id": null,
52
+ "patch_size": 14,
53
+ "prefix": null,
54
+ "problem_type": null,
55
+ "projection_dim" : 768,
56
+ "pruned_heads": {},
57
+ "remove_invalid_values": false,
58
+ "repetition_penalty": 1.0,
59
+ "return_dict": true,
60
+ "return_dict_in_generate": false,
61
+ "sep_token_id": null,
62
+ "task_specific_params": null,
63
+ "temperature": 1.0,
64
+ "tie_encoder_decoder": false,
65
+ "tie_word_embeddings": true,
66
+ "tokenizer_class": null,
67
+ "top_k": 50,
68
+ "top_p": 1.0,
69
+ "torch_dtype": null,
70
+ "torchscript": false,
71
+ "transformers_version": "4.16.0.dev0",
72
+ "use_bfloat16": false
73
+ },
74
+ "text_config": {
75
+ "architectures": [
76
+ "LlamaForCausalLM"
77
+ ],
78
+ "bos_token_id": 1,
79
+ "eos_token_id": 2,
80
+ "hidden_act": "silu",
81
+ "hidden_size": 4096,
82
+ "initializer_range": 0.02,
83
+ "intermediate_size": 11008,
84
+ "max_position_embeddings": 2048,
85
+ "model_type": "llama",
86
+ "num_attention_heads": 32,
87
+ "num_hidden_layers": 32,
88
+ "pad_token_id": 0,
89
+ "rms_norm_eps": 1e-06,
90
+ "tie_word_embeddings": false,
91
+ "torch_dtype": "float16",
92
+ "transformers_version": "4.30.1",
93
+ "use_cache": true,
94
+ "vocab_size": 49958
95
+ },
96
+ "image_size": 224,
97
+ "use_visual_resampler": true,
98
+ "visual_resampler_config": {
99
+ "num_query_tokens": 64,
100
+ "num_hidden_layers": 6,
101
+ "hidden_size": 1024,
102
+ "num_attention_heads": 16,
103
+ "intermediate_size": 4096
104
+ },
105
+ "tie_word_embeddings": false,
106
+ "vocab_size": 49958
107
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": 224,
3
+ "do_center_crop": true,
4
+ "do_normalize": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "CLIPFeatureExtractor",
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "resample": 3,
18
+ "size": 224
19
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<img>",
4
+ "</img>",
5
+ "<pad>",
6
+ "<img_token>"
7
+ ],
8
+ "bos_token": "<s>",
9
+ "eos_token": "</s>",
10
+ "pad_token": "<pad>",
11
+ "unk_token": "<unk>"
12
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d967e855b1213a439df6c8ce2791f869c84b4f3b6cfacf22b86440b8192a2f8
3
+ size 757972
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
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": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "pad_token": null,
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }