ZhangYuanhan commited on
Commit
760dce5
1 Parent(s): 23de648

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/bn/tiktok-mm-2/aiic/users/wujinming/code/work_dir/llavanext-Qwen_Qwen1.5-32B-Chat-google_siglip-so400m-patch14-384-pretrain_blip558k_plain-finetune_la1_6mix_lr1e_5_ufvis_lr1e_6_anyres_d32k_fix",
3
+ "add_faster_video": false,
4
+ "architectures": [
5
+ "LlavaQwenForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 151643,
9
+ "delay_load": false,
10
+ "eos_token_id": 151645,
11
+ "freeze_mm_mlp_adapter": false,
12
+ "freeze_mm_vision_resampler": false,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 5120,
15
+ "image_aspect_ratio": "anyres",
16
+ "image_crop_resolution": 224,
17
+ "image_grid_pinpoints": [
18
+ [
19
+ 384,
20
+ 768
21
+ ],
22
+ [
23
+ 768,
24
+ 384
25
+ ],
26
+ [
27
+ 768,
28
+ 768
29
+ ],
30
+ [
31
+ 1152,
32
+ 384
33
+ ],
34
+ [
35
+ 384,
36
+ 1152
37
+ ]
38
+ ],
39
+ "image_split_resolution": 224,
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 27392,
42
+ "max_position_embeddings": 32768,
43
+ "max_window_layers": 35,
44
+ "mm_hidden_size": 1152,
45
+ "mm_newline_position": "grid",
46
+ "mm_patch_merge_type": "spatial_unpad",
47
+ "mm_pooling_position": "after",
48
+ "mm_projector_lr": null,
49
+ "mm_projector_type": "mlp2x_gelu",
50
+ "mm_resampler_type": null,
51
+ "mm_spatial_pool_mode": "average",
52
+ "mm_spatial_pool_stride": 2,
53
+ "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
54
+ "mm_use_im_patch_token": false,
55
+ "mm_use_im_start_end": false,
56
+ "mm_vision_select_feature": "patch",
57
+ "mm_vision_select_layer": -2,
58
+ "mm_vision_tower": "google/siglip-so400m-patch14-384",
59
+ "mm_vision_tower_lr": null,
60
+ "modality_max_length": "None",
61
+ "model_type": "llava",
62
+ "num_attention_heads": 40,
63
+ "num_hidden_layers": 64,
64
+ "num_key_value_heads": 8,
65
+ "rms_norm_eps": 1e-06,
66
+ "rope_scaling": null,
67
+ "rope_theta": 1000000.0,
68
+ "sliding_window": 32768,
69
+ "tie_word_embeddings": false,
70
+ "tokenizer_model_max_length": 32768,
71
+ "tokenizer_padding_side": "right",
72
+ "torch_dtype": "bfloat16",
73
+ "transformers_version": "4.39.2",
74
+ "tune_mm_mlp_adapter": false,
75
+ "tune_mm_vision_resampler": false,
76
+ "unfreeze_mm_vision_tower": false,
77
+ "use_cache": true,
78
+ "use_mm_proj": true,
79
+ "use_sliding_window": false,
80
+ "vision_tower_pretrained": null,
81
+ "vocab_size": 152064,
82
+ "text_config": {
83
+ "attention_dropout": 0.0,
84
+ "bos_token_id": 151643,
85
+ "eos_token_id": 151643,
86
+ "hidden_act": "silu",
87
+ "hidden_size": 5120,
88
+ "initializer_range": 0.02,
89
+ "intermediate_size": 27392,
90
+ "max_position_embeddings": 32768,
91
+ "max_window_layers": 35,
92
+ "model_type": "qwen2",
93
+ "num_attention_heads": 40,
94
+ "num_hidden_layers": 64,
95
+ "num_key_value_heads": 8,
96
+ "rms_norm_eps": 1e-06,
97
+ "rope_theta": 1000000.0,
98
+ "sliding_window": 32768,
99
+ "tie_word_embeddings": false,
100
+ "torch_dtype": "bfloat16",
101
+ "transformers_version": "4.37.2",
102
+ "use_cache": true,
103
+ "use_sliding_window": false,
104
+ "vocab_size": 152064
105
+ }
106
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attn_implementation": "flash_attention_2",
3
+ "bos_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "pad_token_id": 151643,
10
+ "repetition_penalty": 1.05,
11
+ "temperature": 0.7,
12
+ "top_k": 20,
13
+ "top_p": 0.8,
14
+ "transformers_version": "4.39.2"
15
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5d5cb11831681518b6ee28fa4cfe7d1726396b24ddc5f21864b62eb86b308d
3
+ size 4865526928
model-00002-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f05933ce85b360bdfa787cdfc83c1f1fa83c0725d3fab36626786c6e09352005
3
+ size 4836737752
model-00003-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57198038ac1397fa5e0c46323140faebbd1835c47f5a45fbe10af0e9101404ce
3
+ size 4836737784
model-00004-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6986772209e41e7e242c2ea5dfb607628ac43cb1558fb359828ee3140007520e
3
+ size 4836737816
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b19fb0bb0ee07931fd3183dc967c676ad65a6c00a4c9ac92e7771598e9e6623d
3
+ size 4836737816
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:023916e1168a704f1169246126f32feba42f5b23d0f0689a098dbf95d754ff9f
3
+ size 4836737816
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a262344896da1c1bd6503d85f24613130de80f2288676ab9b2be57c39aee8e9
3
+ size 4836737816
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a429e791dc609def39b8b33d0a2adc5ea9b145f0bc265f02761e1d86a207bd2
3
+ size 4836737816
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78e4a50691dcea506b4b604bfdd02515b6be87cdb7de429142a3ca4721fc46e6
3
+ size 4836737816
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6caeff7d4a246a77f7dbcdbb7a447240a42d154e4286d7ddcedee1f0406822dc
3
+ size 4836737816
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1489722ae57d9f4e2e1ce5cad4c77973e9dffe094c80f5999c1ec490e3f58232
3
+ size 4836737816
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a96e4c1d07f64c2f9f2d09438250dde646668ec39a61941fb0ff2dec98576e2
3
+ size 4836737816
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a899a412a504caef124201dad0a424792348c24b6ba59e6951e5b4587a8316
3
+ size 4836737816
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:080995c944454bd2ebc506f3fcd434d20acaf5946119080afe6b251eccae5b40
3
+ size 2977962744
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "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 %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": null,
40
+ "padding_side": "right",
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "Qwen2Tokenizer",
43
+ "unk_token": null
44
+ }
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:b961d71ce1fcfb58c4bffb7490d420e976d5f5dfd191d11318ca0512811275ff
3
+ size 7864
vocab.json ADDED
The diff for this file is too large to render. See raw diff