Training in progress, step 50
Browse files- added_tokens.json +25 -0
- config.json +55 -0
- merges.txt +0 -0
- special_tokens_map.json +52 -0
- tokenizer.json +0 -0
- tokenizer_config.json +235 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</box>": 151651,
|
3 |
+
"</image>": 151647,
|
4 |
+
"</image_id>": 151659,
|
5 |
+
"</point>": 151655,
|
6 |
+
"</quad>": 151653,
|
7 |
+
"</ref>": 151649,
|
8 |
+
"</slice>": 151657,
|
9 |
+
"<box>": 151650,
|
10 |
+
"<image>": 151646,
|
11 |
+
"<image_id>": 151658,
|
12 |
+
"<point>": 151654,
|
13 |
+
"<quad>": 151652,
|
14 |
+
"<ref>": 151648,
|
15 |
+
"<slice>": 151656,
|
16 |
+
"<|endoftext|>": 151643,
|
17 |
+
"<|im_end|>": 151645,
|
18 |
+
"<|im_start|>": 151644,
|
19 |
+
"<|reserved_special_token_0|>": 151660,
|
20 |
+
"<|reserved_special_token_1|>": 151661,
|
21 |
+
"<|reserved_special_token_2|>": 151662,
|
22 |
+
"<|reserved_special_token_3|>": 151663,
|
23 |
+
"<|reserved_special_token_4|>": 151664,
|
24 |
+
"<|reserved_special_token_5|>": 151665
|
25 |
+
}
|
config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openbmb/MiniCPM-V-2_6",
|
3 |
+
"architectures": [
|
4 |
+
"MiniCPMV"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "openbmb/MiniCPM-V-2_6--configuration_minicpm.MiniCPMVConfig",
|
9 |
+
"AutoModel": "openbmb/MiniCPM-V-2_6--modeling_minicpmv.MiniCPMV",
|
10 |
+
"AutoModelForCausalLM": "openbmb/MiniCPM-V-2_6--modeling_minicpmv.MiniCPMV"
|
11 |
+
},
|
12 |
+
"batch_vision_input": true,
|
13 |
+
"bos_token_id": 151643,
|
14 |
+
"drop_vision_last_layer": false,
|
15 |
+
"eos_token_id": 151645,
|
16 |
+
"hidden_act": "silu",
|
17 |
+
"hidden_size": 3584,
|
18 |
+
"image_size": 448,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 18944,
|
21 |
+
"max_position_embeddings": 32768,
|
22 |
+
"max_window_layers": 28,
|
23 |
+
"model_type": "minicpmv",
|
24 |
+
"num_attention_heads": 28,
|
25 |
+
"num_hidden_layers": 28,
|
26 |
+
"num_key_value_heads": 4,
|
27 |
+
"patch_size": 14,
|
28 |
+
"query_num": 64,
|
29 |
+
"rms_norm_eps": 1e-06,
|
30 |
+
"rope_theta": 1000000.0,
|
31 |
+
"slice_config": {
|
32 |
+
"max_slice_nums": 9,
|
33 |
+
"model_type": "minicpmv"
|
34 |
+
},
|
35 |
+
"slice_mode": true,
|
36 |
+
"sliding_window": 131072,
|
37 |
+
"tie_word_embeddings": false,
|
38 |
+
"torch_dtype": "bfloat16",
|
39 |
+
"transformers_version": "4.40.0",
|
40 |
+
"use_cache": true,
|
41 |
+
"use_image_id": true,
|
42 |
+
"use_sliding_window": false,
|
43 |
+
"version": 2.6,
|
44 |
+
"vision_batch_size": 16,
|
45 |
+
"vision_config": {
|
46 |
+
"hidden_size": 1152,
|
47 |
+
"image_size": 980,
|
48 |
+
"intermediate_size": 4304,
|
49 |
+
"model_type": "siglip_vision_model",
|
50 |
+
"num_attention_heads": 16,
|
51 |
+
"num_hidden_layers": 27,
|
52 |
+
"patch_size": 14
|
53 |
+
},
|
54 |
+
"vocab_size": 151666
|
55 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<image>",
|
4 |
+
"</image>",
|
5 |
+
"<ref>",
|
6 |
+
"</ref>",
|
7 |
+
"<box>",
|
8 |
+
"</box>",
|
9 |
+
"<quad>",
|
10 |
+
"</quad>",
|
11 |
+
"<point>",
|
12 |
+
"</point>",
|
13 |
+
"<slice>",
|
14 |
+
"</slice>",
|
15 |
+
"<image_id>",
|
16 |
+
"</image_id>",
|
17 |
+
"<|reserved_special_token_0|>",
|
18 |
+
"<|reserved_special_token_1|>",
|
19 |
+
"<|reserved_special_token_2|>",
|
20 |
+
"<|reserved_special_token_3|>",
|
21 |
+
"<|reserved_special_token_4|>",
|
22 |
+
"<|reserved_special_token_5|>"
|
23 |
+
],
|
24 |
+
"bos_token": {
|
25 |
+
"content": "<|im_start|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
"eos_token": {
|
32 |
+
"content": "<|im_end|>",
|
33 |
+
"lstrip": false,
|
34 |
+
"normalized": false,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
},
|
38 |
+
"pad_token": {
|
39 |
+
"content": "<|endoftext|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false
|
44 |
+
},
|
45 |
+
"unk_token": {
|
46 |
+
"content": "<unk>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false
|
51 |
+
}
|
52 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,235 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"128244": {
|
5 |
+
"content": "<unk>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151643": {
|
13 |
+
"content": "<|endoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151644": {
|
21 |
+
"content": "<|im_start|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"151645": {
|
29 |
+
"content": "<|im_end|>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"151646": {
|
37 |
+
"content": "<image>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"151647": {
|
45 |
+
"content": "</image>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"151648": {
|
53 |
+
"content": "<ref>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"151649": {
|
61 |
+
"content": "</ref>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"151650": {
|
69 |
+
"content": "<box>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"151651": {
|
77 |
+
"content": "</box>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"151652": {
|
85 |
+
"content": "<quad>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"151653": {
|
93 |
+
"content": "</quad>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"151654": {
|
101 |
+
"content": "<point>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"151655": {
|
109 |
+
"content": "</point>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"151656": {
|
117 |
+
"content": "<slice>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"151657": {
|
125 |
+
"content": "</slice>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"151658": {
|
133 |
+
"content": "<image_id>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
},
|
140 |
+
"151659": {
|
141 |
+
"content": "</image_id>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
+
},
|
148 |
+
"151660": {
|
149 |
+
"content": "<|reserved_special_token_0|>",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": true
|
155 |
+
},
|
156 |
+
"151661": {
|
157 |
+
"content": "<|reserved_special_token_1|>",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": true
|
163 |
+
},
|
164 |
+
"151662": {
|
165 |
+
"content": "<|reserved_special_token_2|>",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": true
|
171 |
+
},
|
172 |
+
"151663": {
|
173 |
+
"content": "<|reserved_special_token_3|>",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": true
|
179 |
+
},
|
180 |
+
"151664": {
|
181 |
+
"content": "<|reserved_special_token_4|>",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": true
|
187 |
+
},
|
188 |
+
"151665": {
|
189 |
+
"content": "<|reserved_special_token_5|>",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": true
|
195 |
+
}
|
196 |
+
},
|
197 |
+
"additional_special_tokens": [
|
198 |
+
"<image>",
|
199 |
+
"</image>",
|
200 |
+
"<ref>",
|
201 |
+
"</ref>",
|
202 |
+
"<box>",
|
203 |
+
"</box>",
|
204 |
+
"<quad>",
|
205 |
+
"</quad>",
|
206 |
+
"<point>",
|
207 |
+
"</point>",
|
208 |
+
"<slice>",
|
209 |
+
"</slice>",
|
210 |
+
"<image_id>",
|
211 |
+
"</image_id>",
|
212 |
+
"<|reserved_special_token_0|>",
|
213 |
+
"<|reserved_special_token_1|>",
|
214 |
+
"<|reserved_special_token_2|>",
|
215 |
+
"<|reserved_special_token_3|>",
|
216 |
+
"<|reserved_special_token_4|>",
|
217 |
+
"<|reserved_special_token_5|>"
|
218 |
+
],
|
219 |
+
"auto_map": {
|
220 |
+
"AutoTokenizer": [
|
221 |
+
"openbmb/MiniCPM-V-2_6--tokenization_minicpmv_fast.MiniCPMVTokenizerFast",
|
222 |
+
null
|
223 |
+
]
|
224 |
+
},
|
225 |
+
"bos_token": "<|im_start|>",
|
226 |
+
"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 %}",
|
227 |
+
"clean_up_tokenization_spaces": false,
|
228 |
+
"eos_token": "<|im_end|>",
|
229 |
+
"errors": "replace",
|
230 |
+
"model_max_length": 1000000000000000019884624838656,
|
231 |
+
"pad_token": "<|endoftext|>",
|
232 |
+
"split_special_tokens": false,
|
233 |
+
"tokenizer_class": "MiniCPMVTokenizer",
|
234 |
+
"unk_token": "<unk>"
|
235 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:834054e26420524b250d0d5a7fff9122ae3740325c0e299ae87a3dadf31625da
|
3 |
+
size 6904
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|