Merged model weights
Browse files- added_tokens.json +33 -0
- config.json +196 -0
- generation_config.json +9 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +40 -0
- tokenizer.json +0 -0
- tokenizer_config.json +289 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</box>": 151673,
|
3 |
+
"</img>": 151666,
|
4 |
+
"</quad>": 151669,
|
5 |
+
"</ref>": 151671,
|
6 |
+
"</tool_call>": 151658,
|
7 |
+
"<IMG_CONTEXT>": 151667,
|
8 |
+
"<box>": 151672,
|
9 |
+
"<img>": 151665,
|
10 |
+
"<quad>": 151668,
|
11 |
+
"<ref>": 151670,
|
12 |
+
"<tool_call>": 151657,
|
13 |
+
"<|box_end|>": 151649,
|
14 |
+
"<|box_start|>": 151648,
|
15 |
+
"<|endoftext|>": 151643,
|
16 |
+
"<|file_sep|>": 151664,
|
17 |
+
"<|fim_middle|>": 151660,
|
18 |
+
"<|fim_pad|>": 151662,
|
19 |
+
"<|fim_prefix|>": 151659,
|
20 |
+
"<|fim_suffix|>": 151661,
|
21 |
+
"<|im_end|>": 151645,
|
22 |
+
"<|im_start|>": 151644,
|
23 |
+
"<|image_pad|>": 151655,
|
24 |
+
"<|object_ref_end|>": 151647,
|
25 |
+
"<|object_ref_start|>": 151646,
|
26 |
+
"<|quad_end|>": 151651,
|
27 |
+
"<|quad_start|>": 151650,
|
28 |
+
"<|repo_name|>": 151663,
|
29 |
+
"<|video_pad|>": 151656,
|
30 |
+
"<|vision_end|>": 151653,
|
31 |
+
"<|vision_pad|>": 151654,
|
32 |
+
"<|vision_start|>": 151652
|
33 |
+
}
|
config.json
ADDED
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_commit_hash": null,
|
3 |
+
"_name_or_path": "../../model_finetuned/intern_v4_action_genome_v1/",
|
4 |
+
"architectures": [
|
5 |
+
"InternVLChatModel"
|
6 |
+
],
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "OpenGVLab/InternVL2_5-1B--configuration_internvl_chat.InternVLChatConfig",
|
9 |
+
"AutoModel": "OpenGVLab/InternVL2_5-1B--modeling_internvl_chat.InternVLChatModel",
|
10 |
+
"AutoModelForCausalLM": "OpenGVLab/InternVL2_5-1B--modeling_internvl_chat.InternVLChatModel"
|
11 |
+
},
|
12 |
+
"downsample_ratio": 0.5,
|
13 |
+
"dynamic_image_size": true,
|
14 |
+
"force_image_size": 448,
|
15 |
+
"hidden_size": 896,
|
16 |
+
"llm_config": {
|
17 |
+
"_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
|
18 |
+
"add_cross_attention": false,
|
19 |
+
"architectures": [
|
20 |
+
"Qwen2ForCausalLM"
|
21 |
+
],
|
22 |
+
"attention_dropout": 0.0,
|
23 |
+
"attn_implementation": "flash_attention_2",
|
24 |
+
"bad_words_ids": null,
|
25 |
+
"begin_suppress_tokens": null,
|
26 |
+
"bos_token_id": 151643,
|
27 |
+
"chunk_size_feed_forward": 0,
|
28 |
+
"cross_attention_hidden_size": null,
|
29 |
+
"decoder_start_token_id": null,
|
30 |
+
"diversity_penalty": 0.0,
|
31 |
+
"do_sample": false,
|
32 |
+
"early_stopping": false,
|
33 |
+
"encoder_no_repeat_ngram_size": 0,
|
34 |
+
"eos_token_id": 151645,
|
35 |
+
"exponential_decay_length_penalty": null,
|
36 |
+
"finetuning_task": null,
|
37 |
+
"forced_bos_token_id": null,
|
38 |
+
"forced_eos_token_id": null,
|
39 |
+
"hidden_act": "silu",
|
40 |
+
"hidden_size": 896,
|
41 |
+
"id2label": {
|
42 |
+
"0": "LABEL_0",
|
43 |
+
"1": "LABEL_1"
|
44 |
+
},
|
45 |
+
"initializer_range": 0.02,
|
46 |
+
"intermediate_size": 4864,
|
47 |
+
"is_decoder": false,
|
48 |
+
"is_encoder_decoder": false,
|
49 |
+
"label2id": {
|
50 |
+
"LABEL_0": 0,
|
51 |
+
"LABEL_1": 1
|
52 |
+
},
|
53 |
+
"length_penalty": 1.0,
|
54 |
+
"max_length": 20,
|
55 |
+
"max_position_embeddings": 32768,
|
56 |
+
"max_window_layers": 21,
|
57 |
+
"min_length": 0,
|
58 |
+
"model_type": "qwen2",
|
59 |
+
"no_repeat_ngram_size": 0,
|
60 |
+
"num_attention_heads": 14,
|
61 |
+
"num_beam_groups": 1,
|
62 |
+
"num_beams": 1,
|
63 |
+
"num_hidden_layers": 24,
|
64 |
+
"num_key_value_heads": 2,
|
65 |
+
"num_return_sequences": 1,
|
66 |
+
"output_attentions": false,
|
67 |
+
"output_hidden_states": false,
|
68 |
+
"output_scores": false,
|
69 |
+
"pad_token_id": null,
|
70 |
+
"prefix": null,
|
71 |
+
"problem_type": null,
|
72 |
+
"pruned_heads": {},
|
73 |
+
"remove_invalid_values": false,
|
74 |
+
"repetition_penalty": 1.0,
|
75 |
+
"return_dict": true,
|
76 |
+
"return_dict_in_generate": false,
|
77 |
+
"rms_norm_eps": 1e-06,
|
78 |
+
"rope_theta": 1000000.0,
|
79 |
+
"sep_token_id": null,
|
80 |
+
"sliding_window": 32768,
|
81 |
+
"suppress_tokens": null,
|
82 |
+
"task_specific_params": null,
|
83 |
+
"temperature": 1.0,
|
84 |
+
"tf_legacy_loss": false,
|
85 |
+
"tie_encoder_decoder": false,
|
86 |
+
"tie_word_embeddings": false,
|
87 |
+
"tokenizer_class": null,
|
88 |
+
"top_k": 50,
|
89 |
+
"top_p": 1.0,
|
90 |
+
"torch_dtype": "bfloat16",
|
91 |
+
"torchscript": false,
|
92 |
+
"transformers_version": "4.37.2",
|
93 |
+
"typical_p": 1.0,
|
94 |
+
"use_bfloat16": true,
|
95 |
+
"use_cache": false,
|
96 |
+
"use_sliding_window": false,
|
97 |
+
"vocab_size": 151674
|
98 |
+
},
|
99 |
+
"max_dynamic_patch": 6,
|
100 |
+
"min_dynamic_patch": 1,
|
101 |
+
"model_type": "internvl_chat",
|
102 |
+
"pad2square": false,
|
103 |
+
"ps_version": "v2",
|
104 |
+
"select_layer": -1,
|
105 |
+
"template": "internvl2_5",
|
106 |
+
"tie_word_embeddings": false,
|
107 |
+
"torch_dtype": "bfloat16",
|
108 |
+
"transformers_version": null,
|
109 |
+
"use_backbone_lora": 0,
|
110 |
+
"use_llm_lora": 0,
|
111 |
+
"use_thumbnail": true,
|
112 |
+
"vision_config": {
|
113 |
+
"_name_or_path": "",
|
114 |
+
"add_cross_attention": false,
|
115 |
+
"architectures": [
|
116 |
+
"InternVisionModel"
|
117 |
+
],
|
118 |
+
"attention_dropout": 0.0,
|
119 |
+
"bad_words_ids": null,
|
120 |
+
"begin_suppress_tokens": null,
|
121 |
+
"bos_token_id": null,
|
122 |
+
"chunk_size_feed_forward": 0,
|
123 |
+
"cross_attention_hidden_size": null,
|
124 |
+
"decoder_start_token_id": null,
|
125 |
+
"diversity_penalty": 0.0,
|
126 |
+
"do_sample": false,
|
127 |
+
"drop_path_rate": 0.0,
|
128 |
+
"dropout": 0.0,
|
129 |
+
"early_stopping": false,
|
130 |
+
"encoder_no_repeat_ngram_size": 0,
|
131 |
+
"eos_token_id": null,
|
132 |
+
"exponential_decay_length_penalty": null,
|
133 |
+
"finetuning_task": null,
|
134 |
+
"forced_bos_token_id": null,
|
135 |
+
"forced_eos_token_id": null,
|
136 |
+
"hidden_act": "gelu",
|
137 |
+
"hidden_size": 1024,
|
138 |
+
"id2label": {
|
139 |
+
"0": "LABEL_0",
|
140 |
+
"1": "LABEL_1"
|
141 |
+
},
|
142 |
+
"image_size": 448,
|
143 |
+
"initializer_factor": 1.0,
|
144 |
+
"initializer_range": 0.02,
|
145 |
+
"intermediate_size": 4096,
|
146 |
+
"is_decoder": false,
|
147 |
+
"is_encoder_decoder": false,
|
148 |
+
"label2id": {
|
149 |
+
"LABEL_0": 0,
|
150 |
+
"LABEL_1": 1
|
151 |
+
},
|
152 |
+
"layer_norm_eps": 1e-06,
|
153 |
+
"length_penalty": 1.0,
|
154 |
+
"max_length": 20,
|
155 |
+
"min_length": 0,
|
156 |
+
"model_type": "intern_vit_6b",
|
157 |
+
"no_repeat_ngram_size": 0,
|
158 |
+
"norm_type": "layer_norm",
|
159 |
+
"num_attention_heads": 16,
|
160 |
+
"num_beam_groups": 1,
|
161 |
+
"num_beams": 1,
|
162 |
+
"num_channels": 3,
|
163 |
+
"num_hidden_layers": 24,
|
164 |
+
"num_return_sequences": 1,
|
165 |
+
"output_attentions": false,
|
166 |
+
"output_hidden_states": false,
|
167 |
+
"output_scores": false,
|
168 |
+
"pad_token_id": null,
|
169 |
+
"patch_size": 14,
|
170 |
+
"prefix": null,
|
171 |
+
"problem_type": null,
|
172 |
+
"pruned_heads": {},
|
173 |
+
"qk_normalization": false,
|
174 |
+
"qkv_bias": true,
|
175 |
+
"remove_invalid_values": false,
|
176 |
+
"repetition_penalty": 1.0,
|
177 |
+
"return_dict": true,
|
178 |
+
"return_dict_in_generate": false,
|
179 |
+
"sep_token_id": null,
|
180 |
+
"suppress_tokens": null,
|
181 |
+
"task_specific_params": null,
|
182 |
+
"temperature": 1.0,
|
183 |
+
"tf_legacy_loss": false,
|
184 |
+
"tie_encoder_decoder": false,
|
185 |
+
"tie_word_embeddings": true,
|
186 |
+
"tokenizer_class": null,
|
187 |
+
"top_k": 50,
|
188 |
+
"top_p": 1.0,
|
189 |
+
"torch_dtype": "bfloat16",
|
190 |
+
"torchscript": false,
|
191 |
+
"transformers_version": "4.37.2",
|
192 |
+
"typical_p": 1.0,
|
193 |
+
"use_bfloat16": true,
|
194 |
+
"use_flash_attn": true
|
195 |
+
}
|
196 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"eos_token_id": [
|
4 |
+
151644,
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"transformers_version": "4.37.2"
|
9 |
+
}
|
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 sha256:62d3e1c38d6f5bb7b8461608ecb230226b88ee3eb9edf650953678d2ba0c8a51
|
3 |
+
size 1876463472
|
special_tokens_map.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>",
|
16 |
+
"<img>",
|
17 |
+
"</img>",
|
18 |
+
"<IMG_CONTEXT>",
|
19 |
+
"<quad>",
|
20 |
+
"</quad>",
|
21 |
+
"<ref>",
|
22 |
+
"</ref>",
|
23 |
+
"<box>",
|
24 |
+
"</box>"
|
25 |
+
],
|
26 |
+
"eos_token": {
|
27 |
+
"content": "<|im_end|>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": false,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
},
|
33 |
+
"pad_token": {
|
34 |
+
"content": "<|endoftext|>",
|
35 |
+
"lstrip": false,
|
36 |
+
"normalized": false,
|
37 |
+
"rstrip": false,
|
38 |
+
"single_word": false
|
39 |
+
}
|
40 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,289 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"151643": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"151644": {
|
15 |
+
"content": "<|im_start|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"151645": {
|
23 |
+
"content": "<|im_end|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"151646": {
|
31 |
+
"content": "<|object_ref_start|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"151647": {
|
39 |
+
"content": "<|object_ref_end|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"151648": {
|
47 |
+
"content": "<|box_start|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"151649": {
|
55 |
+
"content": "<|box_end|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"151650": {
|
63 |
+
"content": "<|quad_start|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"151651": {
|
71 |
+
"content": "<|quad_end|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"151652": {
|
79 |
+
"content": "<|vision_start|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"151653": {
|
87 |
+
"content": "<|vision_end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"151654": {
|
95 |
+
"content": "<|vision_pad|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"151655": {
|
103 |
+
"content": "<|image_pad|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"151656": {
|
111 |
+
"content": "<|video_pad|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"151657": {
|
119 |
+
"content": "<tool_call>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"151658": {
|
127 |
+
"content": "</tool_call>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"151659": {
|
135 |
+
"content": "<|fim_prefix|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"151660": {
|
143 |
+
"content": "<|fim_middle|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"151661": {
|
151 |
+
"content": "<|fim_suffix|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"151662": {
|
159 |
+
"content": "<|fim_pad|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"151663": {
|
167 |
+
"content": "<|repo_name|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"151664": {
|
175 |
+
"content": "<|file_sep|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
},
|
182 |
+
"151665": {
|
183 |
+
"content": "<img>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": true
|
189 |
+
},
|
190 |
+
"151666": {
|
191 |
+
"content": "</img>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": true
|
197 |
+
},
|
198 |
+
"151667": {
|
199 |
+
"content": "<IMG_CONTEXT>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": true
|
205 |
+
},
|
206 |
+
"151668": {
|
207 |
+
"content": "<quad>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": true
|
213 |
+
},
|
214 |
+
"151669": {
|
215 |
+
"content": "</quad>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": true
|
221 |
+
},
|
222 |
+
"151670": {
|
223 |
+
"content": "<ref>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
},
|
230 |
+
"151671": {
|
231 |
+
"content": "</ref>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": true
|
237 |
+
},
|
238 |
+
"151672": {
|
239 |
+
"content": "<box>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": true
|
245 |
+
},
|
246 |
+
"151673": {
|
247 |
+
"content": "</box>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": true
|
253 |
+
}
|
254 |
+
},
|
255 |
+
"additional_special_tokens": [
|
256 |
+
"<|im_start|>",
|
257 |
+
"<|im_end|>",
|
258 |
+
"<|object_ref_start|>",
|
259 |
+
"<|object_ref_end|>",
|
260 |
+
"<|box_start|>",
|
261 |
+
"<|box_end|>",
|
262 |
+
"<|quad_start|>",
|
263 |
+
"<|quad_end|>",
|
264 |
+
"<|vision_start|>",
|
265 |
+
"<|vision_end|>",
|
266 |
+
"<|vision_pad|>",
|
267 |
+
"<|image_pad|>",
|
268 |
+
"<|video_pad|>",
|
269 |
+
"<img>",
|
270 |
+
"</img>",
|
271 |
+
"<IMG_CONTEXT>",
|
272 |
+
"<quad>",
|
273 |
+
"</quad>",
|
274 |
+
"<ref>",
|
275 |
+
"</ref>",
|
276 |
+
"<box>",
|
277 |
+
"</box>"
|
278 |
+
],
|
279 |
+
"bos_token": null,
|
280 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
281 |
+
"clean_up_tokenization_spaces": false,
|
282 |
+
"eos_token": "<|im_end|>",
|
283 |
+
"errors": "replace",
|
284 |
+
"model_max_length": 8192,
|
285 |
+
"pad_token": "<|endoftext|>",
|
286 |
+
"split_special_tokens": false,
|
287 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
288 |
+
"unk_token": null
|
289 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|