ArtusDev commited on
Commit
a762770
·
verified ·
1 Parent(s): f13b391

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ thumbnail: >-
3
+ https://cdn-uploads.huggingface.co/production/uploads/67c10cfba43d7939d60160ff/Cjyto1cPNAwK2f_-uMyLz.png
4
+ language:
5
+ - en
6
+ license: other
7
+ inference: false
8
+ tags:
9
+ - nsfw
10
+ - explicit
11
+ - roleplay
12
+ - mixed-AI
13
+ - furry
14
+ - anthro
15
+ - dark
16
+ - chat
17
+ pipeline_tag: text-generation
18
+ library_name: transformers
19
+ base_model:
20
+ - Aurore-Reveil/Koto-Small-7B-IT
21
+ datasets:
22
+ - Delta-Vector/Hydrus-General-Reasoning
23
+ - Delta-Vector/Hydrus-IF-Mix-Ai2
24
+ - Delta-Vector/Hydrus-Army-Inst
25
+ - Delta-Vector/Hydrus-AM-thinking-Science
26
+ - Delta-Vector/Hydrus-AM-Thinking-Code-Filtered
27
+ - Delta-Vector/Hydrus-AM-Thinking-IF-No-Think
28
+ - Delta-Vector/Hydrus-Tulu-SFT-Mix-V2
29
+ - Delta-Vector/Hydrus-System-Chat-2.0
30
+ - Delta-Vector/Orion-Praxis-Co-Writer
31
+ - Delta-Vector/Orion-Co-Writer-51K
32
+ - Delta-Vector/Orion-Creative_Writing-Complexity
33
+ - Delta-Vector/Orion-vanilla-backrooms-claude-sharegpt
34
+ - Delta-Vector/Hydrus-AM-Thinking-Multi-Turn
35
+ - PocketDoc/Dans-Failuremaxx-Adventure
36
+ - PocketDoc/Dans-Logicmaxx-SAT-AP
37
+ - PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
38
+ - PocketDoc/Dans-Taskmaxx-DataPrepper
39
+ - PocketDoc/Dans-Prosemaxx-Instructwriter-Long
40
+ - PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-2
41
+ - PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-3
42
+ - PocketDoc/Dans-Prosemaxx-InstructWriter-Continue-2
43
+ - PocketDoc/Dans-Systemmaxx
44
+ ---
45
+
46
+ <!--
47
+ COLORS:
48
+ --accent-red: #722F37;
49
+ --accent-grey: #AAAAAA;
50
+ --black: #000000;
51
+ --white: #FFFFFF;
52
+ -->
53
+
54
+ <div style="background-color: #FFFFFF; color: #000000; padding: 28px 18px; border-radius: 10px; width: 100%; border: 1px solid #DDDDDD;">
55
+
56
+ <div align="center">
57
+ <h1 style="color: #000000; margin-bottom: 18px; font-size: 2.1em; font-family:serif;">
58
+ Kuwutu-7B
59
+ </h1>
60
+
61
+ <img
62
+ src="https://cdn-uploads.huggingface.co/production/uploads/67c10cfba43d7939d60160ff/Cjyto1cPNAwK2f_-uMyLz.png"
63
+ width="680px"
64
+ style="border-radius:8px; border:4px solid #000000; box-shadow:0 0 16px #CCCCCC; display:block;"
65
+ alt="Model Thumbnail"
66
+ />
67
+
68
+ <h3 style="color: #722F37; font-style: italic; margin-top: 13px;">Explicit Content Warning</h3>
69
+
70
+ <p style="color: #000000; font-size: 1.13em; font-weight:bold; margin:13px 0 12px 0;">
71
+ <a href="https://discord.gg/aU3a5phBQD" style="color:#000000; text-decoration:underline; font-size:1.17em;"><b>Join our Discord Community&nbsp;&rarr;</b></a>
72
+ </p>
73
+
74
+ <p style="color: #000000; font-size: 0.95em; margin-bottom: 14px;">
75
+ <a href="https://ko-fi.com/mawnipulator" style="color: #000000; text-decoration: underline; font-weight:bold;">Support Mawdistical finetunes here</a>
76
+ </p>
77
+ </div>
78
+
79
+ <div style="background-color: #FFFFFF; color: #000000; padding: 16px; border-radius: 7px; margin: 22px 0; border-left: 3px solid #722F37;">
80
+ <p style="font-style: italic;">
81
+ pleasurable Pain, or is it pain in pleasure?
82
+ </p>
83
+ </div>
84
+
85
+ <hr style="border: 0; height: 1px; background-color: #DDDDDD; margin: 25px 0;">
86
+
87
+ <h2 style="color: #000000; font-size: 1.25em; border-bottom: 1px solid #DDDDDD; padding-bottom: 7px;">✧ Browse the Kuwutu-7B Collection</h2>
88
+ <p>
89
+ <a href="https://huggingface.co/collections/Mawdistical/kuwutu-7b-68b84f0162ccb436f72550cf" style="color: #722F37; text-decoration: underline;">All Kuwutu-7B Quants</a>
90
+ </p>
91
+
92
+ <hr style="border: 0; height: 1px; background-color: #DDDDDD; margin: 25px 0;">
93
+
94
+ <h2 style="color: #000000; font-size: 1.25em; border-bottom: 1px solid #DDDDDD; padding-bottom: 7px;">✧ Recommended Settings</h2>
95
+ <p>
96
+ <strong style="color: #000000;">temperature:</strong> 0.6-0.9<br>
97
+ Experiment to find your taste.
98
+ </p>
99
+
100
+ <hr style="border: 0; height: 1px; background-color: #DDDDDD; margin: 25px 0;">
101
+
102
+ <h2 style="color: #000000; font-size: 1.2em; border-bottom: 1px solid #DDDDDD; padding-bottom: 7px;">✧ Finetuned Set Info</h2>
103
+ <div style="margin-left: 0; font-size:1.07em; margin-bottom:18px;">
104
+ <b style="color: #AAAAAA;">Entries</b><br>
105
+ <span style="margin-left: 2em; color: #000000;">↳ 5400~ Unique Set Scenarios from a pool of 40K</span><br>
106
+
107
+ <b style="color: #AAAAAA;">Entry Composition</b><br>
108
+ <span style="margin-left: 2em; color: #000000;">↳ Heavy Violence</span><br>
109
+ <span style="margin-left: 2em; color: #000000;">↳ Dark Themes</span><br>
110
+ <span style="margin-left: 2em; color: #000000;">↳ Extensive NSFL</span><br>
111
+ <span style="margin-left: 2em; color: #000000;">↳ Non-lethal but enough to scare people.</span><br>
112
+ <span style="margin-left: 2em; color: #000000;">↳ Heavy NSFW</span><br>
113
+ <span style="margin-left: 3em; font-size: 0.9em; color: #555555;">↳ Triggered on user action or passively wherever RP is seen</span><br>
114
+ <span style="margin-left: 2em; color: #000000;">↳ Modern City Scenes</span><br>
115
+ <span style="margin-left: 2em; color: #000000;">↳ Dystopia Scenes</span><br>
116
+ <span style="margin-left: 2em; color: #000000;">↳ Grey Line Consent Scenes</span><br>
117
+ <span style="margin-left: 3em; font-size: 0.9em; color: #555555;">↳ Note: Grey line consent is where consent may be mutual but unspoken at times or considered to be accepted by actions either by character or user. May lead to over-possessiveness in some instances.</span><br>
118
+
119
+ <b style="color: #AAAAAA;">Creation Composition</b><br>
120
+ <span style="margin-left: 2em; color: #000000;">↳ Hybrid Organic-Synthetic mix</span><br>
121
+
122
+ <b style="color: #AAAAAA;">Token Count</b><br>
123
+ <span style="margin-left: 2em; color: #000000;">↳ 21.3 M</span><br>
124
+ <span style="margin-left: 3em; font-size: 0.9em; color: #555555;">↳ Note: token count calculated solely on outputs.</span><br>
125
+
126
+ <b style="color: #AAAAAA;">Type</b><br>
127
+ <span style="margin-left: 2em; color: #000000;">↳ Private In-House</span><br>
128
+
129
+ <b style="color: #AAAAAA;">Focus</b><br>
130
+ <span style="margin-left: 2em; color: #000000;">↳ Male Leaning</span><br>
131
+ <span style="margin-left: 2em; color: #000000;">↳ Anthro</span><br>
132
+ <span style="margin-left: 2em; color: #000000;">↳ Xeno-Likeness</span><br>
133
+ <span style="margin-left: 2em; color: #000000;">↳ Passive Negative Bias with mild narcissistic tendencies, matches energy with subtle languidness.</span><br>
134
+ </div>
135
+
136
+ <hr style="border: 0; height: 1px; background-color: #DDDDDD; margin: 25px 0;">
137
+
138
+ <h2 style="color: #000000; font-size: 1.2em; border-bottom: 1px solid #DDDDDD; padding-bottom: 7px;">✧ Technical Details</h2>
139
+ <div style="margin-left: 0; font-size:1.07em; margin-bottom:18px;">
140
+ <b style="color: #AAAAAA;">Base Model</b> <br>
141
+ <span style="margin-left: 2em; color: #000000;">↳ <a href="https://huggingface.co/Aurore-Reveil/Koto-Small-7B-IT" style="color:#722F37; text-decoration:underline;">Aurore-Reveil/Koto-Small-7B-IT</a></span>
142
+ </div>
143
+
144
+ <div style="margin-left: 0; font-size:1.07em; margin-bottom:18px;">
145
+ <b style="color: #AAAAAA;">Base Model Pre-Training Datasets</b> <br>
146
+ <b style="color: #AAAAAA; margin-left: 1em;">Delta Vector</b> <br>
147
+ <span style="margin-left: 2em; color: #000000;">↳ Hydrus-General-Reasoning</span><br>
148
+ <span style="margin-left: 2em; color: #000000;">↳ Hydrus-IF-Mix-Ai2</span><br>
149
+ <span style="margin-left: 2em; color: #000000;">↳ Hydrus-Army-Inst</span><br>
150
+ <span style="margin-left: 2em; color: #000000;">↳ Hydrus-AM-thinking-Science</span><br>
151
+ <span style="margin-left: 2em; color: #000000;">↳ Hydrus-AM-Thinking-Code-Filtered</span><br>
152
+ <span style="margin-left: 2em; color: #000000;">↳ Hydrus-AM-Thinking-IF-No-Think</span><br>
153
+ <span style="margin-left: 2em; color: #000000;">↳ Hydrus-Tulu-SFT-Mix-V2</span><br>
154
+ <span style="margin-left: 2em; color: #000000;">↳ Hydrus-System-Chat-2.0</span><br>
155
+ <span style="margin-left: 2em; color: #000000;">↳ Orion-Praxis-Co-Writer</span><br>
156
+ <span style="margin-left: 2em; color: #000000;">↳ Orion-Co-Writer-51K</span><br>
157
+ <span style="margin-left: 2em; color: #000000;">↳ Orion-Creative_Writing-Complexity</span><br>
158
+ <span style="margin-left: 2em; color: #000000;">↳ Orion-vanilla-backrooms-claude-sharegpt</span><br>
159
+ <span style="margin-left: 2em; color: #000000;">↳ Hydrus-AM-Thinking-Multi-Turn</span><br>
160
+ <b style="color: #AAAAAA; margin-left: 1em;">PocketDoc</b> <br>
161
+ <span style="margin-left: 2em; color: #000000;">↳ Dans-Failuremaxx-Adventure</span><br>
162
+ <span style="margin-left: 2em; color: #000000;">↳ Dans-Logicmaxx-SAT-AP</span><br>
163
+ <span style="margin-left: 2em; color: #000000;">↳ Dans-MemoryCore-CoreCurriculum-Small</span><br>
164
+ <span style="margin-left: 2em; color: #000000;">↳ Dans-Taskmaxx-DataPrepper</span><br>
165
+ <span style="margin-left: 2em; color: #000000;">↳ Dans-Prosemaxx-Instructwriter-Long</span><br>
166
+ <span style="margin-left: 2em; color: #000000;">↳ Dans-Prosemaxx-InstructWriter-ZeroShot-2</span><br>
167
+ <span style="margin-left: 2em; color: #000000;">↳ Dans-Prosemaxx-InstructWriter-ZeroShot-3</span><br>
168
+ <span style="margin-left: 2em; color: #000000;">↳ Dans-Prosemaxx-InstructWriter-Continue-2</span><br>
169
+ <span style="margin-left: 2em; color: #000000;">↳ Dans-Systemmaxx</span>
170
+ </div>
171
+
172
+ <hr style="border: 0; height: 1px; background-color: #DDDDDD; margin: 25px 0;">
173
+
174
+ <h2 style="color: #000000; font-size: 1.2em; border-bottom: 1px solid #DDDDDD; padding-bottom: 7px;">✧ Credits</h2>
175
+ <div style="margin-left: 5px; font-size:1.07em;">
176
+ <b style="color: #AAAAAA;">Furry Governor</b><br>
177
+ <span style="margin-left: 2em; color: #000000;">↳ <a href="https://vyvan.se" style="color: #722F37; text-decoration: underline;">@Mawnipulator</a></span><br>
178
+ <b style="color: #AAAAAA;">Government Bodies</b><br>
179
+ <span style="margin-left: 2em; color: #000000;">↳ <a href="https://huggingface.co/ArtusDev" style="color: #722F37; text-decoration:underline">@ArtusDev</a></span><br>
180
+ <span style="margin-left: 2em; color: #000000;">↳ <a href="https://huggingface.co/SaisExperiments" style="color: #722F37; text-decoration:underline">@SaisExperiments</a></span><br>
181
+ <span style="margin-left: 2em; color: #000000;">↳ <a href="https://huggingface.co/allura-org" style="color: #722F37; text-decoration:underline">ALLURA-ORG</a></span><br>
182
+ <b style="color: #AAAAAA;">Additional Credits</b><br>
183
+ <span style="margin-left: 2em; color: #000000;">↳ <a href="https://huggingface.co/Fizzarolli" style="color: #722F37; text-decoration: underline;">@Fizzarolli</a></span><br>
184
+ <span style="margin-left: 2em; color: #000000;">↳ <a href="https://huggingface.co/Delta-Vector" style="color: #722F37; text-decoration: underline;">@Delta-Vector</a></span>
185
+ </div>
186
+
187
+ <p style="color: #000000; font-size:1em; margin-top:20px;">
188
+ <strong style="color: #000000;">License:</strong>
189
+ <a href="https://creativecommons.org/licenses/by-nc/4.0/deed.en" style="color: #722F37; text-decoration: underline;">CC BY-NC 4.0</a>
190
+ </p>
191
+ <p style="color: #555555; font-size:0.9em; margin-top:5px;">
192
+ Services such as Arli AI and Featherless AI are granted a CC BY-ND 4.0 license for use of this model.
193
+ </p>
194
+ </div>
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "head_dim": 128,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention"
49
+ ],
50
+ "max_position_embeddings": 32768,
51
+ "max_window_layers": 32,
52
+ "model_type": "qwen2",
53
+ "num_attention_heads": 32,
54
+ "num_hidden_layers": 36,
55
+ "num_key_value_heads": 8,
56
+ "rms_norm_eps": 1e-05,
57
+ "rope_scaling": null,
58
+ "rope_theta": 640000,
59
+ "sliding_window": null,
60
+ "tie_word_embeddings": false,
61
+ "torch_dtype": "bfloat16",
62
+ "transformers_version": "4.55.4",
63
+ "use_cache": true,
64
+ "use_mrope": false,
65
+ "use_sliding_window": false,
66
+ "vocab_size": 151680,
67
+ "quantization_config": {
68
+ "quant_method": "exl3",
69
+ "version": "0.0.6",
70
+ "bits": 5.0,
71
+ "head_bits": 6,
72
+ "calibration": {
73
+ "rows": 100,
74
+ "cols": 2048
75
+ },
76
+ "out_scales": "auto"
77
+ }
78
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": 151643,
5
+ "max_new_tokens": 2048,
6
+ "transformers_version": "4.55.4"
7
+ }
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:ca8acd3a70a50c5904af3cee41ec7da6515eee05648a072198edd5e96092e0ce
3
+ size 5702369240
quantization_config.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff