Upload folder using huggingface_hub (#1)
Browse files- ae9ae7e8c0f65fadfd99332dcb4ceb72ff52733df89c342e49af3720be131c60 (011b9fc36866ef4203f780ea15c9c762b45816eb)
- added_tokens.json +5 -0
- config.json +197 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- vocab.json +0 -0
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 +1,197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/mnt/bn/vl-research/checkpoints/onevision/llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-0.5B-Instruct-pretrain_blip558k_plain-mid_stage_a4",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaQwenForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 896,
|
11 |
+
"image_aspect_ratio": "anyres_max_9",
|
12 |
+
"image_crop_resolution": null,
|
13 |
+
"image_grid_pinpoints": [
|
14 |
+
[
|
15 |
+
384,
|
16 |
+
384
|
17 |
+
],
|
18 |
+
[
|
19 |
+
384,
|
20 |
+
768
|
21 |
+
],
|
22 |
+
[
|
23 |
+
384,
|
24 |
+
1152
|
25 |
+
],
|
26 |
+
[
|
27 |
+
384,
|
28 |
+
1536
|
29 |
+
],
|
30 |
+
[
|
31 |
+
384,
|
32 |
+
1920
|
33 |
+
],
|
34 |
+
[
|
35 |
+
384,
|
36 |
+
2304
|
37 |
+
],
|
38 |
+
[
|
39 |
+
768,
|
40 |
+
384
|
41 |
+
],
|
42 |
+
[
|
43 |
+
768,
|
44 |
+
768
|
45 |
+
],
|
46 |
+
[
|
47 |
+
768,
|
48 |
+
1152
|
49 |
+
],
|
50 |
+
[
|
51 |
+
768,
|
52 |
+
1536
|
53 |
+
],
|
54 |
+
[
|
55 |
+
768,
|
56 |
+
1920
|
57 |
+
],
|
58 |
+
[
|
59 |
+
768,
|
60 |
+
2304
|
61 |
+
],
|
62 |
+
[
|
63 |
+
1152,
|
64 |
+
384
|
65 |
+
],
|
66 |
+
[
|
67 |
+
1152,
|
68 |
+
768
|
69 |
+
],
|
70 |
+
[
|
71 |
+
1152,
|
72 |
+
1152
|
73 |
+
],
|
74 |
+
[
|
75 |
+
1152,
|
76 |
+
1536
|
77 |
+
],
|
78 |
+
[
|
79 |
+
1152,
|
80 |
+
1920
|
81 |
+
],
|
82 |
+
[
|
83 |
+
1152,
|
84 |
+
2304
|
85 |
+
],
|
86 |
+
[
|
87 |
+
1536,
|
88 |
+
384
|
89 |
+
],
|
90 |
+
[
|
91 |
+
1536,
|
92 |
+
768
|
93 |
+
],
|
94 |
+
[
|
95 |
+
1536,
|
96 |
+
1152
|
97 |
+
],
|
98 |
+
[
|
99 |
+
1536,
|
100 |
+
1536
|
101 |
+
],
|
102 |
+
[
|
103 |
+
1536,
|
104 |
+
1920
|
105 |
+
],
|
106 |
+
[
|
107 |
+
1536,
|
108 |
+
2304
|
109 |
+
],
|
110 |
+
[
|
111 |
+
1920,
|
112 |
+
384
|
113 |
+
],
|
114 |
+
[
|
115 |
+
1920,
|
116 |
+
768
|
117 |
+
],
|
118 |
+
[
|
119 |
+
1920,
|
120 |
+
1152
|
121 |
+
],
|
122 |
+
[
|
123 |
+
1920,
|
124 |
+
1536
|
125 |
+
],
|
126 |
+
[
|
127 |
+
1920,
|
128 |
+
1920
|
129 |
+
],
|
130 |
+
[
|
131 |
+
1920,
|
132 |
+
2304
|
133 |
+
],
|
134 |
+
[
|
135 |
+
2304,
|
136 |
+
384
|
137 |
+
],
|
138 |
+
[
|
139 |
+
2304,
|
140 |
+
768
|
141 |
+
],
|
142 |
+
[
|
143 |
+
2304,
|
144 |
+
1152
|
145 |
+
],
|
146 |
+
[
|
147 |
+
2304,
|
148 |
+
1536
|
149 |
+
],
|
150 |
+
[
|
151 |
+
2304,
|
152 |
+
1920
|
153 |
+
],
|
154 |
+
[
|
155 |
+
2304,
|
156 |
+
2304
|
157 |
+
]
|
158 |
+
],
|
159 |
+
"image_split_resolution": null,
|
160 |
+
"initializer_range": 0.02,
|
161 |
+
"intermediate_size": 4864,
|
162 |
+
"max_position_embeddings": 32768,
|
163 |
+
"max_window_layers": 24,
|
164 |
+
"mm_hidden_size": 1152,
|
165 |
+
"mm_patch_merge_type": "spatial_unpad",
|
166 |
+
"mm_projector_lr": null,
|
167 |
+
"mm_projector_type": "mlp2x_gelu",
|
168 |
+
"mm_resampler_type": null,
|
169 |
+
"mm_spatial_pool_mode": "bilinear",
|
170 |
+
"mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
|
171 |
+
"mm_use_im_patch_token": false,
|
172 |
+
"mm_use_im_start_end": false,
|
173 |
+
"mm_vision_select_feature": "patch",
|
174 |
+
"mm_vision_select_layer": -2,
|
175 |
+
"mm_vision_tower": "google/siglip-so400m-patch14-384",
|
176 |
+
"mm_vision_tower_lr": 2e-06,
|
177 |
+
"model_type": "qwen2",
|
178 |
+
"num_attention_heads": 14,
|
179 |
+
"num_hidden_layers": 24,
|
180 |
+
"num_key_value_heads": 2,
|
181 |
+
"pos_skipping_range": 4096,
|
182 |
+
"rms_norm_eps": 1e-06,
|
183 |
+
"rope_scaling": null,
|
184 |
+
"rope_theta": 1000000.0,
|
185 |
+
"sliding_window": 32768,
|
186 |
+
"tie_word_embeddings": true,
|
187 |
+
"tokenizer_model_max_length": 32768,
|
188 |
+
"tokenizer_padding_side": "right",
|
189 |
+
"torch_dtype": "bfloat16",
|
190 |
+
"transformers_version": "4.40.0.dev0",
|
191 |
+
"use_cache": true,
|
192 |
+
"use_mm_proj": true,
|
193 |
+
"use_pos_skipping": false,
|
194 |
+
"use_sliding_window": false,
|
195 |
+
"vision_tower_pretrained": null,
|
196 |
+
"vocab_size": 151936
|
197 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
+
"repetition_penalty": 1.1,
|
10 |
+
"temperature": 0.7,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.40.0.dev0"
|
14 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:684e9c48505f5f876eabeb6a1e257793e3ebce5cd298f029d4cd43a7978c8aa3
|
3 |
+
size 1787335336
|
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 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|endoftext|>",
|
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 sha256:8a90fcca6dbb284844fb8dd5e4884a3f1ff26cf774c39d2135e6b5c3f5656dcb
|
3 |
+
size 7864
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|