Vision-CAIR commited on
Commit
1a9af44
1 Parent(s): a1cd5fc

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +83 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +20 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +53 -0
  6. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/tmp/iopath_cache/manifold_cache/tree/users/shenx/finetune/09051611-cambrian_qwenvl_t576_ov",
3
+ "architectures": [
4
+ "CambrianQwenForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 151643,
9
+ "connect_layer": 2,
10
+ "connector_depth": 3,
11
+ "connector_only": true,
12
+ "dino_threshold": 0.83,
13
+ "drop_threshold": 0.7,
14
+ "eos_token_id": 151645,
15
+ "frame_pos": false,
16
+ "freeze_mm_mlp_adapter": false,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 3584,
19
+ "highres": true,
20
+ "highres_connect": false,
21
+ "image_aspect_ratio": "pad",
22
+ "image_position": 91,
23
+ "image_token_len": 144,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 18944,
26
+ "is_st_sampler": false,
27
+ "lowres_token": 8,
28
+ "max_position_embeddings": 32768,
29
+ "max_window_layers": 28,
30
+ "mm_patch_merge_type": "flat",
31
+ "mm_projector_lr": null,
32
+ "mm_projector_type": "sva",
33
+ "mm_use_im_patch_token": false,
34
+ "mm_use_im_start_end": false,
35
+ "mm_vision_sampler_lr": null,
36
+ "mm_vision_select_feature": "patch",
37
+ "mm_vision_select_layer": -2,
38
+ "mm_vision_tower_aux_list": [
39
+ "siglip/CLIP-ViT-SO400M-14-384",
40
+ "facebook/dinov2-giant-res378"
41
+ ],
42
+ "mm_vision_tower_aux_token_len_list": [
43
+ 576,
44
+ 576
45
+ ],
46
+ "mm_vision_tower_lr": null,
47
+ "model_type": "cambrian_qwen",
48
+ "num_attention_heads": 28,
49
+ "num_hidden_layers": 28,
50
+ "num_key_value_heads": 4,
51
+ "num_of_vision_sampler_layers": 10,
52
+ "num_query_group": 1,
53
+ "pretraining_tp": 1,
54
+ "query_num_list": [
55
+ 144
56
+ ],
57
+ "rms_norm_eps": 1e-06,
58
+ "rope_scaling": null,
59
+ "rope_theta": 1000000.0,
60
+ "sliding_window": null,
61
+ "spmd_debug": null,
62
+ "spmd_fsdp_sharding": null,
63
+ "spmd_mesh": null,
64
+ "start_of_vision_sampler_layers": 0,
65
+ "stride_of_vision_sampler_layers": 3,
66
+ "tie_word_embeddings": false,
67
+ "tokenizer_model_max_length": 10000,
68
+ "tokenizer_padding_side": "right",
69
+ "torch_dtype": "float32",
70
+ "transformers_version": "4.44.2",
71
+ "tune_mm_mlp_adapter": false,
72
+ "unfreeze_mm_vision_tower": false,
73
+ "use_cache": false,
74
+ "use_mm_proj": true,
75
+ "use_pos_skipping": false,
76
+ "use_sliding_window": false,
77
+ "vision_hidden_size": 1024,
78
+ "vision_tower_aux_token_len_list": [
79
+ 576,
80
+ 576
81
+ ],
82
+ "vocab_size": 152064
83
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<image>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "additional_special_tokens": [
38
+ "<|im_start|>",
39
+ "<|im_end|>"
40
+ ],
41
+ "bos_token": null,
42
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
43
+ "clean_up_tokenization_spaces": false,
44
+ "eos_token": "<|im_end|>",
45
+ "errors": "replace",
46
+ "model_max_length": 32768,
47
+ "pad_token": "<|endoftext|>",
48
+ "padding_side": "right",
49
+ "processor_class": "LlavaProcessor",
50
+ "split_special_tokens": false,
51
+ "tokenizer_class": "Qwen2Tokenizer",
52
+ "unk_token": null
53
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff