Backup-bdg commited on
Commit
3a1df72
·
verified ·
1 Parent(s): e2adcb4

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -1,3 +1,14 @@
1
  model.safetensors filter=lfs diff=lfs merge=lfs -text
2
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
3
  training_state.pt filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
1
  model.safetensors filter=lfs diff=lfs merge=lfs -text
2
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
3
  training_state.pt filter=lfs diff=lfs merge=lfs -text
4
+ audio_decoder.safetensors filter=lfs diff=lfs merge=lfs -text
5
+ audio_encoder.safetensors filter=lfs diff=lfs merge=lfs -text
6
+ audio_projector.safetensors filter=lfs diff=lfs merge=lfs -text
7
+ cross_attention.safetensors filter=lfs diff=lfs merge=lfs -text
8
+ generator.safetensors filter=lfs diff=lfs merge=lfs -text
9
+ llm.safetensors filter=lfs diff=lfs merge=lfs -text
10
+ projector.safetensors filter=lfs diff=lfs merge=lfs -text
11
+ video_encoder.safetensors filter=lfs diff=lfs merge=lfs -text
12
+ video_generator.safetensors filter=lfs diff=lfs merge=lfs -text
13
+ vision_encoder.safetensors filter=lfs diff=lfs merge=lfs -text
14
+ waveform_decoder.safetensors filter=lfs diff=lfs merge=lfs -text
audio_decoder.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b0558451b5a8ee083e17a15deaa6fbd61081954477e7dfa15506d2a602213d
3
+ size 2788209752
audio_encoder.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47edc19a3e4225f602556af592208e410f2b0c0ee0412cffe3e1650ca8cf0d89
3
+ size 689538704
audio_projector.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43003dc667e1777c275530155bf980a62d08b878062a9e63b7e797fc5debd66f
3
+ size 4198552
chat_template.jinja ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set bos = '<|bos|>' -%}
2
+ {%- set eos = '<|eos|>' -%}
3
+ {%- set system_start = '<|system|>' -%}
4
+ {%- set system_end = '<|/system|>' -%}
5
+ {%- set user_start = '<|user|>' -%}
6
+ {%- set user_end = '<|/user|>' -%}
7
+ {%- set assistant_start = '<|assistant|>' -%}
8
+ {%- set assistant_end = '<|/assistant|>' -%}
9
+ {%- set image_start = '<|image|>' -%}
10
+ {%- set image_end = '<|/image|>' -%}
11
+ {%- set video_start = '<|video|>' -%}
12
+ {%- set video_end = '<|/video|>' -%}
13
+ {%- set audio_start = '<|audio|>' -%}
14
+ {%- set audio_end = '<|/audio|>' -%}
15
+ {%- set doc_start = '<|doc|>' -%}
16
+ {%- set doc_end = '<|/doc|>' -%}
17
+ {%- set tool_call_start = '<|tool_call|>' -%}
18
+ {%- set tool_call_end = '<|/tool_call|>' -%}
19
+ {%- set tool_result_start = '<|tool_result|>' -%}
20
+ {%- set tool_result_end = '<|/tool_result|>' -%}
21
+ {%- set tools_start = '<|tools|>' -%}
22
+ {%- set tools_end = '<|/tools|>' -%}
23
+ {%- set available_tools_start = '<|available_tools|>' -%}
24
+ {%- set available_tools_end = '<|/available_tools|>' -%}
25
+ {%- set function_name_start = '<|function_name|>' -%}
26
+ {%- set function_name_end = '<|/function_name|>' -%}
27
+ {%- set function_args_start = '<|function_args|>' -%}
28
+ {%- set function_args_end = '<|/function_args|>' -%}
29
+ {%- set think_start = '<|think|>' -%}
30
+ {%- set think_end = '<|/think|>' -%}
31
+ {%- set plan_start = '<|plan|>' -%}
32
+ {%- set plan_end = '<|/plan|>' -%}
33
+ {%- set critique_start = '<|critique|>' -%}
34
+ {%- set critique_end = '<|/critique|>' -%}
35
+ {%- set analysis_start = '<|analysis|>' -%}
36
+ {%- set analysis_end = '<|/analysis|>' -%}
37
+ {%- set observation_start = '<|observation|>' -%}
38
+ {%- set observation_end = '<|/observation|>' -%}
39
+ {%- set reflection_start = '<|reflection|>' -%}
40
+ {%- set reflection_end = '<|/reflection|>' -%}
41
+ {%- set conclusion_start = '<|conclusion|>' -%}
42
+ {%- set conclusion_end = '<|/conclusion|>' -%}
43
+ {%- set code_start = '<|code|>' -%}
44
+ {%- set code_end = '<|/code|>' -%}
45
+ {%- set exec_start = '<|exec|>' -%}
46
+ {%- set exec_end = '<|/exec|>' -%}
47
+ {%- set exec_result = '<|exec_result|>' -%}
48
+ {%- set exec_result_end = '<|/exec_result|>' -%}
49
+ {%- set jupyter_code = '<|jupyter_code|>' -%}
50
+ {%- set jupyter_code_end = '<|/jupyter_code|>' -%}
51
+ {%- set jupyter_output = '<|jupyter_output|>' -%}
52
+ {%- set jupyter_output_end = '<|/jupyter_output|>' -%}
53
+ {%- set gen_image_start = '<|gen_image|>' -%}
54
+ {%- set gen_image_end = '<|/gen_image|>' -%}
55
+ {%- set gen_video_start = '<|gen_video|>' -%}
56
+ {%- set gen_video_end = '<|/gen_video|>' -%}
57
+ {%- set speak_start = '<|speak|>' -%}
58
+ {%- set speak_end = '<|/speak|>' -%}
59
+ {%- set listen_start = '<|listen|>' -%}
60
+ {%- set listen_end = '<|/listen|>' -%}
61
+ {%- set memory_start = '<|memory|>' -%}
62
+ {%- set memory_end = '<|/memory|>' -%}
63
+ {%- set context_start = '<|context|>' -%}
64
+ {%- set context_end = '<|/context|>' -%}
65
+ {%- set uncertain_start = '<|uncertain|>' -%}
66
+ {%- set uncertain_end = '<|/uncertain|>' -%}
67
+ {%- set cite_start = '<|cite|>' -%}
68
+ {%- set cite_end = '<|/cite|>' -%}
69
+ {%- set eod = '<|eod|>' -%}
70
+
71
+ {{- bos -}}
72
+ {%- if messages[0]['role'] == 'system' -%}
73
+ {{- system_start + messages[0]['content'] + system_end -}}
74
+ {%- set messages = messages[1:] -%}
75
+ {%- endif -%}
76
+ {%- if available_tools is defined and available_tools -%}
77
+ {{- available_tools_start + available_tools + available_tools_end -}}
78
+ {%- elif tools is defined and tools -%}
79
+ {{- tools_start + tools + tools_end -}}
80
+ {%- endif -%}
81
+ {%- if memory is defined and memory -%}
82
+ {{- memory_start + memory + memory_end -}}
83
+ {%- endif -%}
84
+ {%- if context is defined and context -%}
85
+ {{- context_start + context + context_end -}}
86
+ {%- endif -%}
87
+ {%- for message in messages -%}
88
+ {%- if message['role'] == 'system' -%}
89
+ {{- system_start + message['content'] + system_end -}}
90
+ {%- elif message['role'] == 'user' -%}
91
+ {{- user_start -}}
92
+ {%- if message.get('images') -%}
93
+ {%- for img in message['images'] -%}
94
+ {{- image_start + img + image_end -}}
95
+ {%- endfor -%}
96
+ {%- endif -%}
97
+ {%- if message.get('videos') -%}
98
+ {%- for vid in message['videos'] -%}
99
+ {{- video_start + vid + video_end -}}
100
+ {%- endfor -%}
101
+ {%- endif -%}
102
+ {%- if message.get('audio') -%}
103
+ {%- for aud in message['audio'] -%}
104
+ {{- audio_start + aud + audio_end -}}
105
+ {%- endfor -%}
106
+ {%- endif -%}
107
+ {%- if message.get('documents') -%}
108
+ {%- for doc in message['documents'] -%}
109
+ {{- doc_start + doc + doc_end -}}
110
+ {%- endfor -%}
111
+ {%- endif -%}
112
+ {{- message['content'] + user_end -}}
113
+ {%- elif message['role'] == 'assistant' -%}
114
+ {{- assistant_start -}}
115
+ {%- if message.get('thinking') -%}
116
+ {{- think_start + message['thinking'] + think_end -}}
117
+ {%- endif -%}
118
+ {%- if message.get('planning') -%}
119
+ {{- plan_start + message['planning'] + plan_end -}}
120
+ {%- endif -%}
121
+ {%- if message.get('analysis') -%}
122
+ {{- analysis_start + message['analysis'] + analysis_end -}}
123
+ {%- endif -%}
124
+ {%- if message.get('observation') -%}
125
+ {{- observation_start + message['observation'] + observation_end -}}
126
+ {%- endif -%}
127
+ {%- if message.get('reflection') -%}
128
+ {{- reflection_start + message['reflection'] + reflection_end -}}
129
+ {%- endif -%}
130
+ {%- if message.get('critique') -%}
131
+ {{- critique_start + message['critique'] + critique_end -}}
132
+ {%- endif -%}
133
+ {%- if message.get('conclusion') -%}
134
+ {{- conclusion_start + message['conclusion'] + conclusion_end -}}
135
+ {%- endif -%}
136
+ {%- if message.get('tool_calls') -%}
137
+ {%- for tool in message['tool_calls'] -%}
138
+ {{- tool_call_start -}}
139
+ {%- if tool is mapping -%}
140
+ {{- function_name_start + tool.get('name', '') + function_name_end -}}
141
+ {{- function_args_start + (tool.get('arguments', '') | tojson if tool.get('arguments') is mapping else tool.get('arguments', '')) + function_args_end -}}
142
+ {%- else -%}
143
+ {{- tool -}}
144
+ {%- endif -%}
145
+ {{- tool_call_end -}}
146
+ {%- endfor -%}
147
+ {%- endif -%}
148
+ {%- if message.get('code') -%}
149
+ {{- code_start + message['code'] + code_end -}}
150
+ {%- endif -%}
151
+ {%- if message.get('exec') -%}
152
+ {{- exec_start + message['exec'] + exec_end -}}
153
+ {%- endif -%}
154
+ {%- if message.get('gen_image') -%}
155
+ {{- gen_image_start + message['gen_image'] + gen_image_end -}}
156
+ {%- endif -%}
157
+ {%- if message.get('gen_video') -%}
158
+ {{- gen_video_start + message['gen_video'] + gen_video_end -}}
159
+ {%- endif -%}
160
+ {%- if message.get('speak') -%}
161
+ {{- speak_start + message['speak'] + speak_end -}}
162
+ {%- endif -%}
163
+ {%- if message.get('uncertain') -%}
164
+ {{- uncertain_start + message['uncertain'] + uncertain_end -}}
165
+ {%- endif -%}
166
+ {%- if message.get('citation') -%}
167
+ {{- cite_start + message['citation'] + cite_end -}}
168
+ {%- endif -%}
169
+ {{- message['content'] -}}
170
+ {%- if not loop.last or add_generation_prompt is not defined or not add_generation_prompt -%}
171
+ {{- assistant_end -}}
172
+ {%- endif -%}
173
+ {%- elif message['role'] == 'tool' -%}
174
+ {{- tool_result_start + message['content'] + tool_result_end -}}
175
+ {%- elif message['role'] == 'exec_result' -%}
176
+ {{- exec_result + message['content'] + exec_result_end -}}
177
+ {%- elif message['role'] == 'jupyter' -%}
178
+ {{- jupyter_output + message['content'] + jupyter_output_end -}}
179
+ {%- endif -%}
180
+ {%- endfor -%}
181
+ {%- if add_generation_prompt is defined and add_generation_prompt -%}
182
+ {{- assistant_start -}}
183
+ {%- if enable_thinking is defined and enable_thinking -%}
184
+ {{- think_start -}}
185
+ {%- endif -%}
186
+ {%- endif -%}
components.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "components": [
3
+ "llm",
4
+ "vision_encoder",
5
+ "video_encoder",
6
+ "audio_encoder",
7
+ "audio_decoder",
8
+ "projector",
9
+ "audio_projector",
10
+ "cross_attention",
11
+ "generator",
12
+ "video_generator",
13
+ "waveform_decoder",
14
+ "modality_markers"
15
+ ],
16
+ "save_format": "components"
17
+ }
config.json ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "Xoron-Dev-MultiMoE",
3
+ "hidden_size": 1024,
4
+ "num_layers": 12,
5
+ "num_heads": 16,
6
+ "intermediate_size": 2048,
7
+ "vocab_size": 151643,
8
+ "max_position_embeddings": 131072,
9
+ "rms_norm_eps": 1e-06,
10
+ "use_ring_attention": true,
11
+ "ring_attention_chunk_size": 4096,
12
+ "tie_word_embeddings": true,
13
+ "use_moe": true,
14
+ "num_experts": 8,
15
+ "num_experts_per_tok": 2,
16
+ "moe_layer_freq": 2,
17
+ "use_shared_expert": true,
18
+ "moe_capacity_factor": 1.25,
19
+ "use_aux_lossless": true,
20
+ "vision_model_name": "google/siglip-so400m-patch14-384",
21
+ "freeze_vision": false,
22
+ "num_vision_tokens": 64,
23
+ "projector_type": "perceiver",
24
+ "use_vision_dual_stream": true,
25
+ "use_vision_titok": true,
26
+ "num_vision_titok_tokens": 256,
27
+ "num_vision_dual_stream_layers": 2,
28
+ "use_video_3d_rope": true,
29
+ "use_video_temporal_moe": true,
30
+ "num_video_encoder_layers": 4,
31
+ "num_video_experts": 4,
32
+ "use_multi_scale": true,
33
+ "image_scales": [
34
+ [
35
+ 128,
36
+ 128
37
+ ],
38
+ [
39
+ 192,
40
+ 192
41
+ ],
42
+ [
43
+ 256,
44
+ 256
45
+ ],
46
+ [
47
+ 320,
48
+ 320
49
+ ],
50
+ [
51
+ 384,
52
+ 384
53
+ ],
54
+ [
55
+ 448,
56
+ 448
57
+ ],
58
+ [
59
+ 512,
60
+ 512
61
+ ]
62
+ ],
63
+ "image_scale_probs": [
64
+ 0.05,
65
+ 0.1,
66
+ 0.3,
67
+ 0.25,
68
+ 0.15,
69
+ 0.1,
70
+ 0.05
71
+ ],
72
+ "image_min_size": 128,
73
+ "image_max_size": 512,
74
+ "image_base_size": 256,
75
+ "video_scales": [
76
+ [
77
+ 128,
78
+ 128
79
+ ],
80
+ [
81
+ 192,
82
+ 192
83
+ ],
84
+ [
85
+ 256,
86
+ 256
87
+ ],
88
+ [
89
+ 320,
90
+ 320
91
+ ],
92
+ [
93
+ 384,
94
+ 384
95
+ ]
96
+ ],
97
+ "video_scale_probs": [
98
+ 0.1,
99
+ 0.2,
100
+ 0.35,
101
+ 0.25,
102
+ 0.1
103
+ ],
104
+ "video_min_size": 128,
105
+ "video_max_size": 384,
106
+ "video_base_size": 256,
107
+ "video_frame_scales": [
108
+ 8,
109
+ 12,
110
+ 16,
111
+ 20,
112
+ 24,
113
+ 32
114
+ ],
115
+ "video_frame_scale_probs": [
116
+ 0.1,
117
+ 0.15,
118
+ 0.3,
119
+ 0.2,
120
+ 0.15,
121
+ 0.1
122
+ ],
123
+ "video_min_frames": 8,
124
+ "video_max_frames": 32,
125
+ "video_base_frames": 16,
126
+ "multi_scale_strategy": "random",
127
+ "multi_scale_warmup_epochs": 5,
128
+ "generation_supported_sizes": [
129
+ 256,
130
+ 320,
131
+ 384,
132
+ 448,
133
+ 512
134
+ ],
135
+ "generation_supported_frames": [
136
+ 8,
137
+ 12,
138
+ 16,
139
+ 20,
140
+ 24,
141
+ 32
142
+ ],
143
+ "enable_generation": true,
144
+ "generation_latent_channels": 4,
145
+ "generation_base_channels": 128,
146
+ "generation_inference_steps": 50,
147
+ "generation_cfg_scale": 7.5,
148
+ "generation_use_flow_matching": true,
149
+ "generation_num_experts": 4,
150
+ "generation_use_dual_stream": true,
151
+ "generation_video_cfg_scale": 7.5,
152
+ "generation_video_use_flow_matching": true,
153
+ "generation_video_num_experts": 4,
154
+ "generation_video_use_3d_rope": true,
155
+ "generation_video_use_temporal_moe": true,
156
+ "audio_sample_rate": 16000,
157
+ "audio_n_mels": 80,
158
+ "audio_max_length": 1000,
159
+ "audio_num_speakers": 256,
160
+ "use_raw_waveform": true,
161
+ "audio_kv_lora_rank": 256,
162
+ "audio_speaker_embed_dim": 256,
163
+ "use_mas": true,
164
+ "use_in_context_audio_prompting": true,
165
+ "tokenizer_name": "Qwen/Qwen2.5-1.5B",
166
+ "use_lora": true,
167
+ "lora_r": 32,
168
+ "lora_alpha": 64,
169
+ "lora_dropout": 0.05,
170
+ "lora_target_modules": [
171
+ "q_proj",
172
+ "k_proj",
173
+ "v_proj",
174
+ "o_proj",
175
+ "gate_proj",
176
+ "up_proj",
177
+ "down_proj"
178
+ ],
179
+ "train_lora_only": false,
180
+ "use_rslora": true,
181
+ "use_dora": false,
182
+ "lora_plus_lr_ratio": 4.0,
183
+ "use_cross_attention": true,
184
+ "cross_attention_layers": 4,
185
+ "cross_attention_heads": 8,
186
+ "cross_attention_dropout": 0.1,
187
+ "use_flash_attention": true,
188
+ "output_dir": "./xoron-model",
189
+ "has_audio_encoder": true,
190
+ "has_audio_decoder": true,
191
+ "has_waveform_decoder": true,
192
+ "has_vision_encoder": true,
193
+ "has_video_encoder": true,
194
+ "has_generator": true,
195
+ "has_video_generator": true,
196
+ "has_cross_attention": true,
197
+ "lora_applied": true,
198
+ "architecture_version": 2
199
+ }
cross_attention.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:142eff322380538b068e0c78114e797473b12d72f3bfe769bd353b19b0bb4204
3
+ size 348361664
generator.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3193c75a5585dde156ec1cce53f924d1c6c9db84964b3e3f7b2561e02f74cdda
3
+ size 1258822080
llm.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b40cf5aaf30bd17af85dab0fab917187c07e230c766dd47b634b0c229c6a11a
3
+ size 3012498960
modality_markers.safetensors ADDED
Binary file (25 kB). View file
 
projector.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7d9e0fded469d0089346bbbf366ead991d0bdfcef50dd20b9b59de10016bbeb
3
+ size 105757984
special_tokens.json ADDED
@@ -0,0 +1,410 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos": "<|bos|>",
3
+ "eos": "<|eos|>",
4
+ "pad": "<|pad|>",
5
+ "prompt_start": "<|prompt|>",
6
+ "prompt_end": "<|/prompt|>",
7
+ "text_start": "<|text|>",
8
+ "text_end": "<|/text|>",
9
+ "response_start": "<|response|>",
10
+ "response_end": "<|/response|>",
11
+ "system_start": "<|system|>",
12
+ "system_end": "<|/system|>",
13
+ "user_start": "<|user|>",
14
+ "user_end": "<|/user|>",
15
+ "assistant_start": "<|assistant|>",
16
+ "assistant_end": "<|/assistant|>",
17
+ "memory_start": "<|memory|>",
18
+ "memory_end": "<|/memory|>",
19
+ "working_memory_start": "<|working_memory|>",
20
+ "working_memory_end": "<|/working_memory|>",
21
+ "long_term_memory_start": "<|long_term_memory|>",
22
+ "long_term_memory_end": "<|/long_term_memory|>",
23
+ "summary_start": "<|summary|>",
24
+ "summary_end": "<|/summary|>",
25
+ "condensed_start": "<|condensed|>",
26
+ "condensed_end": "<|/condensed|>",
27
+ "user_profile_start": "<|user_profile|>",
28
+ "user_profile_end": "<|/user_profile|>",
29
+ "user_preference_start": "<|user_pref|>",
30
+ "user_preference_end": "<|/user_pref|>",
31
+ "hard_rule_start": "<|hard_rule|>",
32
+ "hard_rule_end": "<|/hard_rule|>",
33
+ "session_start": "<|session|>",
34
+ "session_end": "<|/session|>",
35
+ "conversation_history_start": "<|conv_history|>",
36
+ "conversation_history_end": "<|/conv_history|>",
37
+ "fim_prefix": "<|fim_prefix|>",
38
+ "fim_middle": "<|fim_middle|>",
39
+ "fim_suffix": "<|fim_suffix|>",
40
+ "fim_pad": "<|fim_pad|>",
41
+ "commit_before": "<|commit_before|>",
42
+ "commit_before_end": "<|/commit_before|>",
43
+ "commit_after": "<|commit_after|>",
44
+ "commit_after_end": "<|/commit_after|>",
45
+ "commit_msg": "<|commit_msg|>",
46
+ "commit_msg_end": "<|/commit_msg|>",
47
+ "diff_start": "<|diff|>",
48
+ "diff_end": "<|/diff|>",
49
+ "diff_add": "<|diff_add|>",
50
+ "diff_del": "<|diff_del|>",
51
+ "diff_context": "<|diff_ctx|>",
52
+ "reponame": "<|reponame|>",
53
+ "reponame_end": "<|/reponame|>",
54
+ "gh_stars": "<|gh_stars|>",
55
+ "gh_stars_end": "<|/gh_stars|>",
56
+ "branch": "<|branch|>",
57
+ "branch_end": "<|/branch|>",
58
+ "issue_start": "<|issue|>",
59
+ "issue_end": "<|/issue|>",
60
+ "issue_title": "<|issue_title|>",
61
+ "issue_title_end": "<|/issue_title|>",
62
+ "issue_body": "<|issue_body|>",
63
+ "issue_body_end": "<|/issue_body|>",
64
+ "issue_closed": "<|issue_closed|>",
65
+ "issue_open": "<|issue_open|>",
66
+ "pr_start": "<|pr|>",
67
+ "pr_end": "<|/pr|>",
68
+ "pr_title": "<|pr_title|>",
69
+ "pr_title_end": "<|/pr_title|>",
70
+ "pr_body": "<|pr_body|>",
71
+ "pr_body_end": "<|/pr_body|>",
72
+ "pr_merged": "<|pr_merged|>",
73
+ "pr_closed": "<|pr_closed|>",
74
+ "jupyter_start": "<|jupyter|>",
75
+ "jupyter_end": "<|/jupyter|>",
76
+ "jupyter_code": "<|jupyter_code|>",
77
+ "jupyter_code_end": "<|/jupyter_code|>",
78
+ "jupyter_output": "<|jupyter_output|>",
79
+ "jupyter_output_end": "<|/jupyter_output|>",
80
+ "jupyter_text": "<|jupyter_text|>",
81
+ "jupyter_text_end": "<|/jupyter_text|>",
82
+ "jupyter_error": "<|jupyter_error|>",
83
+ "jupyter_error_end": "<|/jupyter_error|>",
84
+ "empty_output": "<|empty_output|>",
85
+ "exec_start": "<|exec|>",
86
+ "exec_end": "<|/exec|>",
87
+ "exec_result": "<|exec_result|>",
88
+ "exec_result_end": "<|/exec_result|>",
89
+ "exec_error": "<|exec_error|>",
90
+ "exec_error_end": "<|/exec_error|>",
91
+ "exec_timeout": "<|exec_timeout|>",
92
+ "add_file": "<|add_file|>",
93
+ "add_file_end": "<|/add_file|>",
94
+ "delete_file": "<|delete_file|>",
95
+ "delete_file_end": "<|/delete_file|>",
96
+ "rename_file": "<|rename_file|>",
97
+ "rename_file_end": "<|/rename_file|>",
98
+ "edit_file": "<|edit_file|>",
99
+ "edit_file_end": "<|/edit_file|>",
100
+ "read_file": "<|read_file|>",
101
+ "read_file_end": "<|/read_file|>",
102
+ "file_sep": "<|file_sep|>",
103
+ "file_content": "<|file_content|>",
104
+ "file_content_end": "<|/file_content|>",
105
+ "edit_range": "<|edit_range|>",
106
+ "edit_range_end": "<|/edit_range|>",
107
+ "line_num": "<|line|>",
108
+ "line_num_end": "<|/line|>",
109
+ "insert_before": "<|insert_before|>",
110
+ "insert_after": "<|insert_after|>",
111
+ "replace": "<|replace|>",
112
+ "replace_end": "<|/replace|>",
113
+ "encoder_start": "[e~[",
114
+ "encoder_end": "]~e]",
115
+ "decoder_start": "[d~[",
116
+ "decoder_end": "]~d]",
117
+ "projection_start": "[p~[",
118
+ "projection_end": "]~p]",
119
+ "state_begin": "]~b]",
120
+ "state_end": "]~!b[",
121
+ "modal_switch": "[m~[",
122
+ "modal_switch_end": "]~m]",
123
+ "doc_start": "<|doc|>",
124
+ "doc_end": "<|/doc|>",
125
+ "eod": "<|eod|>",
126
+ "file_txt": "<|file:txt|>",
127
+ "file_txt_end": "<|/file:txt|>",
128
+ "file_md": "<|file:md|>",
129
+ "file_md_end": "<|/file:md|>",
130
+ "file_json": "<|file:json|>",
131
+ "file_json_end": "<|/file:json|>",
132
+ "file_xml": "<|file:xml|>",
133
+ "file_xml_end": "<|/file:xml|>",
134
+ "file_yaml": "<|file:yaml|>",
135
+ "file_yaml_end": "<|/file:yaml|>",
136
+ "file_html": "<|file:html|>",
137
+ "file_html_end": "<|/file:html|>",
138
+ "file_css": "<|file:css|>",
139
+ "file_css_end": "<|/file:css|>",
140
+ "file_csv": "<|file:csv|>",
141
+ "file_csv_end": "<|/file:csv|>",
142
+ "file_toml": "<|file:toml|>",
143
+ "file_toml_end": "<|/file:toml|>",
144
+ "file_ini": "<|file:ini|>",
145
+ "file_ini_end": "<|/file:ini|>",
146
+ "file_log": "<|file:log|>",
147
+ "file_log_end": "<|/file:log|>",
148
+ "filename_start": "<|filename|>",
149
+ "filename_end": "<|/filename|>",
150
+ "filepath_start": "<|filepath|>",
151
+ "filepath_end": "<|/filepath|>",
152
+ "image_start": "<|image|>",
153
+ "image_end": "<|/image|>",
154
+ "video_start": "<|video|>",
155
+ "video_end": "<|/video|>",
156
+ "timestamp_start": "<|timestamp|>",
157
+ "timestamp_end": "<|/timestamp|>",
158
+ "time_range_start": "<|time_range|>",
159
+ "time_range_end": "<|/time_range|>",
160
+ "keyframe": "<|keyframe|>",
161
+ "keyframe_end": "<|/keyframe|>",
162
+ "scene_change": "<|scene_change|>",
163
+ "scene_start": "<|scene|>",
164
+ "scene_end": "<|/scene|>",
165
+ "segment_start": "<|segment|>",
166
+ "segment_end": "<|/segment|>",
167
+ "frame_start": "<|frame|>",
168
+ "frame_end": "<|/frame|>",
169
+ "frame_num": "<|frame_num|>",
170
+ "frame_num_end": "<|/frame_num|>",
171
+ "action_start": "<|action|>",
172
+ "action_end": "<|/action|>",
173
+ "event_start": "<|event|>",
174
+ "event_end": "<|/event|>",
175
+ "region_start": "<|region|>",
176
+ "region_end": "<|/region|>",
177
+ "bbox_start": "<|bbox|>",
178
+ "bbox_end": "<|/bbox|>",
179
+ "object_start": "<|object|>",
180
+ "object_end": "<|/object|>",
181
+ "gen_image_start": "<|gen_image|>",
182
+ "gen_image_end": "<|/gen_image|>",
183
+ "gen_video_start": "<|gen_video|>",
184
+ "gen_video_end": "<|/gen_video|>",
185
+ "tool_call_start": "<|tool_call|>",
186
+ "tool_call_end": "<|/tool_call|>",
187
+ "tool_result_start": "<|tool_result|>",
188
+ "tool_result_end": "<|/tool_result|>",
189
+ "function_name_start": "<|function_name|>",
190
+ "function_name_end": "<|/function_name|>",
191
+ "function_args_start": "<|function_args|>",
192
+ "function_args_end": "<|/function_args|>",
193
+ "arg_name_start": "<|arg_name|>",
194
+ "arg_name_end": "<|/arg_name|>",
195
+ "arg_value_start": "<|arg_value|>",
196
+ "arg_value_end": "<|/arg_value|>",
197
+ "tools_start": "<|tools|>",
198
+ "tools_end": "<|/tools|>",
199
+ "function_def_start": "<|function_def|>",
200
+ "function_def_end": "<|/function_def|>",
201
+ "available_tools_start": "<|available_tools|>",
202
+ "available_tools_end": "<|/available_tools|>",
203
+ "tool_def_start": "<|tool_def|>",
204
+ "tool_def_end": "<|/tool_def|>",
205
+ "tool_name": "<|tool_name|>",
206
+ "tool_name_end": "<|/tool_name|>",
207
+ "tool_description": "<|tool_desc|>",
208
+ "tool_description_end": "<|/tool_desc|>",
209
+ "tool_params_start": "<|tool_params|>",
210
+ "tool_params_end": "<|/tool_params|>",
211
+ "param_name": "<|param_name|>",
212
+ "param_name_end": "<|/param_name|>",
213
+ "param_type": "<|param_type|>",
214
+ "param_type_end": "<|/param_type|>",
215
+ "param_required": "<|param_required|>",
216
+ "param_optional": "<|param_optional|>",
217
+ "tool_error_start": "<|tool_error|>",
218
+ "tool_error_end": "<|/tool_error|>",
219
+ "tool_success": "<|tool_success|>",
220
+ "tool_calls_start": "<|tool_calls|>",
221
+ "tool_calls_end": "<|/tool_calls|>",
222
+ "tool_id_start": "<|tool_id|>",
223
+ "tool_id_end": "<|/tool_id|>",
224
+ "code_start": "<|code|>",
225
+ "code_end": "<|/code|>",
226
+ "lang_python": "<|lang:python|>",
227
+ "lang_javascript": "<|lang:javascript|>",
228
+ "lang_typescript": "<|lang:typescript|>",
229
+ "lang_java": "<|lang:java|>",
230
+ "lang_cpp": "<|lang:cpp|>",
231
+ "lang_c": "<|lang:c|>",
232
+ "lang_csharp": "<|lang:csharp|>",
233
+ "lang_go": "<|lang:go|>",
234
+ "lang_rust": "<|lang:rust|>",
235
+ "lang_ruby": "<|lang:ruby|>",
236
+ "lang_php": "<|lang:php|>",
237
+ "lang_swift": "<|lang:swift|>",
238
+ "lang_kotlin": "<|lang:kotlin|>",
239
+ "lang_scala": "<|lang:scala|>",
240
+ "lang_shell": "<|lang:shell|>",
241
+ "lang_bash": "<|lang:bash|>",
242
+ "lang_sql": "<|lang:sql|>",
243
+ "lang_r": "<|lang:r|>",
244
+ "lang_matlab": "<|lang:matlab|>",
245
+ "lang_lua": "<|lang:lua|>",
246
+ "lang_perl": "<|lang:perl|>",
247
+ "lang_haskell": "<|lang:haskell|>",
248
+ "lang_other": "<|lang:other|>",
249
+ "think_start": "<|think|>",
250
+ "think_end": "<|/think|>",
251
+ "observation_start": "<|observation|>",
252
+ "observation_end": "<|/observation|>",
253
+ "note_start": "<|note|>",
254
+ "note_end": "<|/note|>",
255
+ "step_start": "<|step|>",
256
+ "step_end": "<|/step|>",
257
+ "reflection_start": "<|reflection|>",
258
+ "reflection_end": "<|/reflection|>",
259
+ "hypothesis_start": "<|hypothesis|>",
260
+ "hypothesis_end": "<|/hypothesis|>",
261
+ "conclusion_start": "<|conclusion|>",
262
+ "conclusion_end": "<|/conclusion|>",
263
+ "plan_start": "<|plan|>",
264
+ "plan_end": "<|/plan|>",
265
+ "plan_step": "<|plan_step|>",
266
+ "plan_step_end": "<|/plan_step|>",
267
+ "critique_start": "<|critique|>",
268
+ "critique_end": "<|/critique|>",
269
+ "error_found": "<|error_found|>",
270
+ "no_error": "<|no_error|>",
271
+ "analysis_start": "<|analysis|>",
272
+ "analysis_end": "<|/analysis|>",
273
+ "breakdown_start": "<|breakdown|>",
274
+ "breakdown_end": "<|/breakdown|>",
275
+ "decision_start": "<|decision|>",
276
+ "decision_end": "<|/decision|>",
277
+ "option_start": "<|option|>",
278
+ "option_end": "<|/option|>",
279
+ "chosen": "<|chosen|>",
280
+ "rejected": "<|rejected|>",
281
+ "because": "<|because|>",
282
+ "therefore": "<|therefore|>",
283
+ "however": "<|however|>",
284
+ "alternatively": "<|alternatively|>",
285
+ "confidence_high": "<|confidence:high|>",
286
+ "confidence_medium": "<|confidence:medium|>",
287
+ "confidence_low": "<|confidence:low|>",
288
+ "confidence_uncertain": "<|confidence:uncertain|>",
289
+ "uncertainty_score": "<|uncertainty_score|>",
290
+ "uncertainty_score_end": "<|/uncertainty_score|>",
291
+ "certainty_score": "<|certainty_score|>",
292
+ "certainty_score_end": "<|/certainty_score|>",
293
+ "uncertain_start": "<|uncertain|>",
294
+ "uncertain_end": "<|/uncertain|>",
295
+ "unknown": "<|unknown|>",
296
+ "need_verification": "<|need_verify|>",
297
+ "may_be_outdated": "<|may_outdated|>",
298
+ "speculative": "<|speculative|>",
299
+ "approximate": "<|approximate|>",
300
+ "verify_start": "<|verify|>",
301
+ "verify_end": "<|/verify|>",
302
+ "fact_check": "<|fact_check|>",
303
+ "self_correct": "<|self_correct|>",
304
+ "correction_start": "<|correction|>",
305
+ "correction_end": "<|/correction|>",
306
+ "retract": "<|retract|>",
307
+ "clarify": "<|clarify|>",
308
+ "cite_start": "<|cite|>",
309
+ "cite_end": "<|/cite|>",
310
+ "source_start": "<|source|>",
311
+ "source_end": "<|/source|>",
312
+ "reference_start": "<|ref|>",
313
+ "reference_end": "<|/ref|>",
314
+ "quote_start": "<|quote|>",
315
+ "quote_end": "<|/quote|>",
316
+ "attribution": "<|attribution|>",
317
+ "attribution_end": "<|/attribution|>",
318
+ "context_start": "<|context|>",
319
+ "context_end": "<|/context|>",
320
+ "retrieved_start": "<|retrieved|>",
321
+ "retrieved_end": "<|/retrieved|>",
322
+ "grounded": "<|grounded|>",
323
+ "ungrounded": "<|ungrounded|>",
324
+ "partially_grounded": "<|partially_grounded|>",
325
+ "knowledge_cutoff": "<|knowledge_cutoff|>",
326
+ "beyond_knowledge": "<|beyond_knowledge|>",
327
+ "within_knowledge": "<|within_knowledge|>",
328
+ "knowledge_date": "<|knowledge_date|>",
329
+ "knowledge_date_end": "<|/knowledge_date|>",
330
+ "listen_start": "<|listen|>",
331
+ "listen_end": "<|/listen|>",
332
+ "speak_start": "<|speak|>",
333
+ "speak_end": "<|/speak|>",
334
+ "audio_start": "<|audio|>",
335
+ "audio_end": "<|/audio|>",
336
+ "audio_prompt_start": "<|audio_prompt|>",
337
+ "audio_prompt_end": "<|/audio_prompt|>",
338
+ "speaker_ref_start": "<|speaker_ref|>",
339
+ "speaker_ref_end": "<|/speaker_ref|>",
340
+ "table_start": "<|table|>",
341
+ "table_end": "<|/table|>",
342
+ "table_row_start": "<|row|>",
343
+ "table_row_end": "<|/row|>",
344
+ "table_cell_start": "<|cell|>",
345
+ "table_cell_end": "<|/cell|>",
346
+ "table_header_start": "<|thead|>",
347
+ "table_header_end": "<|/thead|>",
348
+ "table_body_start": "<|tbody|>",
349
+ "table_body_end": "<|/tbody|>",
350
+ "schema_start": "<|schema|>",
351
+ "schema_end": "<|/schema|>",
352
+ "schema_field": "<|field|>",
353
+ "schema_field_end": "<|/field|>",
354
+ "schema_type": "<|type|>",
355
+ "schema_type_end": "<|/type|>",
356
+ "schema_required": "<|required|>",
357
+ "schema_optional": "<|optional|>",
358
+ "version": "<|version|>",
359
+ "version_end": "<|/version|>",
360
+ "deprecated": "<|deprecated|>",
361
+ "since": "<|since|>",
362
+ "since_end": "<|/since|>",
363
+ "changelog_start": "<|changelog|>",
364
+ "changelog_end": "<|/changelog|>",
365
+ "json_start": "<|json|>",
366
+ "json_end": "<|/json|>",
367
+ "xml_start": "<|xml|>",
368
+ "xml_end": "<|/xml|>",
369
+ "yaml_start": "<|yaml|>",
370
+ "yaml_end": "<|/yaml|>",
371
+ "csv_start": "<|csv|>",
372
+ "csv_end": "<|/csv|>",
373
+ "list_start": "<|list|>",
374
+ "list_end": "<|/list|>",
375
+ "list_item": "<|item|>",
376
+ "list_item_end": "<|/item|>",
377
+ "ordered_list": "<|ol|>",
378
+ "ordered_list_end": "<|/ol|>",
379
+ "unordered_list": "<|ul|>",
380
+ "unordered_list_end": "<|/ul|>",
381
+ "kv_start": "<|kv|>",
382
+ "kv_end": "<|/kv|>",
383
+ "key_start": "<|key|>",
384
+ "key_end": "<|/key|>",
385
+ "value_start": "<|value|>",
386
+ "value_end": "<|/value|>",
387
+ "task_start": "<|task|>",
388
+ "task_end": "<|/task|>",
389
+ "task_type": "<|task_type|>",
390
+ "task_type_end": "<|/task_type|>",
391
+ "instruction_start": "<|instruction|>",
392
+ "instruction_end": "<|/instruction|>",
393
+ "constraint_start": "<|constraint|>",
394
+ "constraint_end": "<|/constraint|>",
395
+ "example_start": "<|example|>",
396
+ "example_end": "<|/example|>",
397
+ "input_start": "<|input|>",
398
+ "input_end": "<|/input|>",
399
+ "output_start": "<|output|>",
400
+ "output_end": "<|/output|>",
401
+ "expected_start": "<|expected|>",
402
+ "expected_end": "<|/expected|>",
403
+ "separator": "<|sep|>",
404
+ "newline": "<|nl|>",
405
+ "mask": "<|mask|>",
406
+ "ellipsis": "<|...|>",
407
+ "continuation": "<|cont|>",
408
+ "truncated": "<|truncated|>",
409
+ "redacted": "<|redacted|>"
410
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa9c470e506980aeb8552c4c6fc87fe50a19637fc1bfd0ab77a8422f26a8f89f
3
+ size 11498197
tokenizer_config.json ADDED
@@ -0,0 +1,424 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|bos|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|eos|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|bos|>",
10
+ "<|eos|>",
11
+ "<|pad|>",
12
+ "<|prompt|>",
13
+ "<|/prompt|>",
14
+ "<|text|>",
15
+ "<|/text|>",
16
+ "<|response|>",
17
+ "<|/response|>",
18
+ "<|system|>",
19
+ "<|/system|>",
20
+ "<|user|>",
21
+ "<|/user|>",
22
+ "<|assistant|>",
23
+ "<|/assistant|>",
24
+ "<|memory|>",
25
+ "<|/memory|>",
26
+ "<|working_memory|>",
27
+ "<|/working_memory|>",
28
+ "<|long_term_memory|>",
29
+ "<|/long_term_memory|>",
30
+ "<|summary|>",
31
+ "<|/summary|>",
32
+ "<|condensed|>",
33
+ "<|/condensed|>",
34
+ "<|user_profile|>",
35
+ "<|/user_profile|>",
36
+ "<|user_pref|>",
37
+ "<|/user_pref|>",
38
+ "<|hard_rule|>",
39
+ "<|/hard_rule|>",
40
+ "<|session|>",
41
+ "<|/session|>",
42
+ "<|conv_history|>",
43
+ "<|/conv_history|>",
44
+ "<|fim_prefix|>",
45
+ "<|fim_middle|>",
46
+ "<|fim_suffix|>",
47
+ "<|fim_pad|>",
48
+ "<|commit_before|>",
49
+ "<|/commit_before|>",
50
+ "<|commit_after|>",
51
+ "<|/commit_after|>",
52
+ "<|commit_msg|>",
53
+ "<|/commit_msg|>",
54
+ "<|diff|>",
55
+ "<|/diff|>",
56
+ "<|diff_add|>",
57
+ "<|diff_del|>",
58
+ "<|diff_ctx|>",
59
+ "<|reponame|>",
60
+ "<|/reponame|>",
61
+ "<|gh_stars|>",
62
+ "<|/gh_stars|>",
63
+ "<|branch|>",
64
+ "<|/branch|>",
65
+ "<|issue|>",
66
+ "<|/issue|>",
67
+ "<|issue_title|>",
68
+ "<|/issue_title|>",
69
+ "<|issue_body|>",
70
+ "<|/issue_body|>",
71
+ "<|issue_closed|>",
72
+ "<|issue_open|>",
73
+ "<|pr|>",
74
+ "<|/pr|>",
75
+ "<|pr_title|>",
76
+ "<|/pr_title|>",
77
+ "<|pr_body|>",
78
+ "<|/pr_body|>",
79
+ "<|pr_merged|>",
80
+ "<|pr_closed|>",
81
+ "<|jupyter|>",
82
+ "<|/jupyter|>",
83
+ "<|jupyter_code|>",
84
+ "<|/jupyter_code|>",
85
+ "<|jupyter_output|>",
86
+ "<|/jupyter_output|>",
87
+ "<|jupyter_text|>",
88
+ "<|/jupyter_text|>",
89
+ "<|jupyter_error|>",
90
+ "<|/jupyter_error|>",
91
+ "<|empty_output|>",
92
+ "<|exec|>",
93
+ "<|/exec|>",
94
+ "<|exec_result|>",
95
+ "<|/exec_result|>",
96
+ "<|exec_error|>",
97
+ "<|/exec_error|>",
98
+ "<|exec_timeout|>",
99
+ "<|add_file|>",
100
+ "<|/add_file|>",
101
+ "<|delete_file|>",
102
+ "<|/delete_file|>",
103
+ "<|rename_file|>",
104
+ "<|/rename_file|>",
105
+ "<|edit_file|>",
106
+ "<|/edit_file|>",
107
+ "<|read_file|>",
108
+ "<|/read_file|>",
109
+ "<|file_sep|>",
110
+ "<|file_content|>",
111
+ "<|/file_content|>",
112
+ "<|edit_range|>",
113
+ "<|/edit_range|>",
114
+ "<|line|>",
115
+ "<|/line|>",
116
+ "<|insert_before|>",
117
+ "<|insert_after|>",
118
+ "<|replace|>",
119
+ "<|/replace|>",
120
+ "[e~[",
121
+ "]~e]",
122
+ "[d~[",
123
+ "]~d]",
124
+ "[p~[",
125
+ "]~p]",
126
+ "]~b]",
127
+ "]~!b[",
128
+ "[m~[",
129
+ "]~m]",
130
+ "<|doc|>",
131
+ "<|/doc|>",
132
+ "<|eod|>",
133
+ "<|file:txt|>",
134
+ "<|/file:txt|>",
135
+ "<|file:md|>",
136
+ "<|/file:md|>",
137
+ "<|file:json|>",
138
+ "<|/file:json|>",
139
+ "<|file:xml|>",
140
+ "<|/file:xml|>",
141
+ "<|file:yaml|>",
142
+ "<|/file:yaml|>",
143
+ "<|file:html|>",
144
+ "<|/file:html|>",
145
+ "<|file:css|>",
146
+ "<|/file:css|>",
147
+ "<|file:csv|>",
148
+ "<|/file:csv|>",
149
+ "<|file:toml|>",
150
+ "<|/file:toml|>",
151
+ "<|file:ini|>",
152
+ "<|/file:ini|>",
153
+ "<|file:log|>",
154
+ "<|/file:log|>",
155
+ "<|filename|>",
156
+ "<|/filename|>",
157
+ "<|filepath|>",
158
+ "<|/filepath|>",
159
+ "<|image|>",
160
+ "<|/image|>",
161
+ "<|video|>",
162
+ "<|/video|>",
163
+ "<|timestamp|>",
164
+ "<|/timestamp|>",
165
+ "<|time_range|>",
166
+ "<|/time_range|>",
167
+ "<|keyframe|>",
168
+ "<|/keyframe|>",
169
+ "<|scene_change|>",
170
+ "<|scene|>",
171
+ "<|/scene|>",
172
+ "<|segment|>",
173
+ "<|/segment|>",
174
+ "<|frame|>",
175
+ "<|/frame|>",
176
+ "<|frame_num|>",
177
+ "<|/frame_num|>",
178
+ "<|action|>",
179
+ "<|/action|>",
180
+ "<|event|>",
181
+ "<|/event|>",
182
+ "<|region|>",
183
+ "<|/region|>",
184
+ "<|bbox|>",
185
+ "<|/bbox|>",
186
+ "<|object|>",
187
+ "<|/object|>",
188
+ "<|gen_image|>",
189
+ "<|/gen_image|>",
190
+ "<|gen_video|>",
191
+ "<|/gen_video|>",
192
+ "<|tool_call|>",
193
+ "<|/tool_call|>",
194
+ "<|tool_result|>",
195
+ "<|/tool_result|>",
196
+ "<|function_name|>",
197
+ "<|/function_name|>",
198
+ "<|function_args|>",
199
+ "<|/function_args|>",
200
+ "<|arg_name|>",
201
+ "<|/arg_name|>",
202
+ "<|arg_value|>",
203
+ "<|/arg_value|>",
204
+ "<|tools|>",
205
+ "<|/tools|>",
206
+ "<|function_def|>",
207
+ "<|/function_def|>",
208
+ "<|available_tools|>",
209
+ "<|/available_tools|>",
210
+ "<|tool_def|>",
211
+ "<|/tool_def|>",
212
+ "<|tool_name|>",
213
+ "<|/tool_name|>",
214
+ "<|tool_desc|>",
215
+ "<|/tool_desc|>",
216
+ "<|tool_params|>",
217
+ "<|/tool_params|>",
218
+ "<|param_name|>",
219
+ "<|/param_name|>",
220
+ "<|param_type|>",
221
+ "<|/param_type|>",
222
+ "<|param_required|>",
223
+ "<|param_optional|>",
224
+ "<|tool_error|>",
225
+ "<|/tool_error|>",
226
+ "<|tool_success|>",
227
+ "<|tool_calls|>",
228
+ "<|/tool_calls|>",
229
+ "<|tool_id|>",
230
+ "<|/tool_id|>",
231
+ "<|code|>",
232
+ "<|/code|>",
233
+ "<|lang:python|>",
234
+ "<|lang:javascript|>",
235
+ "<|lang:typescript|>",
236
+ "<|lang:java|>",
237
+ "<|lang:cpp|>",
238
+ "<|lang:c|>",
239
+ "<|lang:csharp|>",
240
+ "<|lang:go|>",
241
+ "<|lang:rust|>",
242
+ "<|lang:ruby|>",
243
+ "<|lang:php|>",
244
+ "<|lang:swift|>",
245
+ "<|lang:kotlin|>",
246
+ "<|lang:scala|>",
247
+ "<|lang:shell|>",
248
+ "<|lang:bash|>",
249
+ "<|lang:sql|>",
250
+ "<|lang:r|>",
251
+ "<|lang:matlab|>",
252
+ "<|lang:lua|>",
253
+ "<|lang:perl|>",
254
+ "<|lang:haskell|>",
255
+ "<|lang:other|>",
256
+ "<|think|>",
257
+ "<|/think|>",
258
+ "<|observation|>",
259
+ "<|/observation|>",
260
+ "<|note|>",
261
+ "<|/note|>",
262
+ "<|step|>",
263
+ "<|/step|>",
264
+ "<|reflection|>",
265
+ "<|/reflection|>",
266
+ "<|hypothesis|>",
267
+ "<|/hypothesis|>",
268
+ "<|conclusion|>",
269
+ "<|/conclusion|>",
270
+ "<|plan|>",
271
+ "<|/plan|>",
272
+ "<|plan_step|>",
273
+ "<|/plan_step|>",
274
+ "<|critique|>",
275
+ "<|/critique|>",
276
+ "<|error_found|>",
277
+ "<|no_error|>",
278
+ "<|analysis|>",
279
+ "<|/analysis|>",
280
+ "<|breakdown|>",
281
+ "<|/breakdown|>",
282
+ "<|decision|>",
283
+ "<|/decision|>",
284
+ "<|option|>",
285
+ "<|/option|>",
286
+ "<|chosen|>",
287
+ "<|rejected|>",
288
+ "<|because|>",
289
+ "<|therefore|>",
290
+ "<|however|>",
291
+ "<|alternatively|>",
292
+ "<|confidence:high|>",
293
+ "<|confidence:medium|>",
294
+ "<|confidence:low|>",
295
+ "<|confidence:uncertain|>",
296
+ "<|uncertainty_score|>",
297
+ "<|/uncertainty_score|>",
298
+ "<|certainty_score|>",
299
+ "<|/certainty_score|>",
300
+ "<|uncertain|>",
301
+ "<|/uncertain|>",
302
+ "<|unknown|>",
303
+ "<|need_verify|>",
304
+ "<|may_outdated|>",
305
+ "<|speculative|>",
306
+ "<|approximate|>",
307
+ "<|verify|>",
308
+ "<|/verify|>",
309
+ "<|fact_check|>",
310
+ "<|self_correct|>",
311
+ "<|correction|>",
312
+ "<|/correction|>",
313
+ "<|retract|>",
314
+ "<|clarify|>",
315
+ "<|cite|>",
316
+ "<|/cite|>",
317
+ "<|source|>",
318
+ "<|/source|>",
319
+ "<|ref|>",
320
+ "<|/ref|>",
321
+ "<|quote|>",
322
+ "<|/quote|>",
323
+ "<|attribution|>",
324
+ "<|/attribution|>",
325
+ "<|context|>",
326
+ "<|/context|>",
327
+ "<|retrieved|>",
328
+ "<|/retrieved|>",
329
+ "<|grounded|>",
330
+ "<|ungrounded|>",
331
+ "<|partially_grounded|>",
332
+ "<|knowledge_cutoff|>",
333
+ "<|beyond_knowledge|>",
334
+ "<|within_knowledge|>",
335
+ "<|knowledge_date|>",
336
+ "<|/knowledge_date|>",
337
+ "<|listen|>",
338
+ "<|/listen|>",
339
+ "<|speak|>",
340
+ "<|/speak|>",
341
+ "<|audio|>",
342
+ "<|/audio|>",
343
+ "<|audio_prompt|>",
344
+ "<|/audio_prompt|>",
345
+ "<|speaker_ref|>",
346
+ "<|/speaker_ref|>",
347
+ "<|table|>",
348
+ "<|/table|>",
349
+ "<|row|>",
350
+ "<|/row|>",
351
+ "<|cell|>",
352
+ "<|/cell|>",
353
+ "<|thead|>",
354
+ "<|/thead|>",
355
+ "<|tbody|>",
356
+ "<|/tbody|>",
357
+ "<|schema|>",
358
+ "<|/schema|>",
359
+ "<|field|>",
360
+ "<|/field|>",
361
+ "<|type|>",
362
+ "<|/type|>",
363
+ "<|required|>",
364
+ "<|optional|>",
365
+ "<|version|>",
366
+ "<|/version|>",
367
+ "<|deprecated|>",
368
+ "<|since|>",
369
+ "<|/since|>",
370
+ "<|changelog|>",
371
+ "<|/changelog|>",
372
+ "<|json|>",
373
+ "<|/json|>",
374
+ "<|xml|>",
375
+ "<|/xml|>",
376
+ "<|yaml|>",
377
+ "<|/yaml|>",
378
+ "<|csv|>",
379
+ "<|/csv|>",
380
+ "<|list|>",
381
+ "<|/list|>",
382
+ "<|item|>",
383
+ "<|/item|>",
384
+ "<|ol|>",
385
+ "<|/ol|>",
386
+ "<|ul|>",
387
+ "<|/ul|>",
388
+ "<|kv|>",
389
+ "<|/kv|>",
390
+ "<|key|>",
391
+ "<|/key|>",
392
+ "<|value|>",
393
+ "<|/value|>",
394
+ "<|task|>",
395
+ "<|/task|>",
396
+ "<|task_type|>",
397
+ "<|/task_type|>",
398
+ "<|instruction|>",
399
+ "<|/instruction|>",
400
+ "<|constraint|>",
401
+ "<|/constraint|>",
402
+ "<|example|>",
403
+ "<|/example|>",
404
+ "<|input|>",
405
+ "<|/input|>",
406
+ "<|output|>",
407
+ "<|/output|>",
408
+ "<|expected|>",
409
+ "<|/expected|>",
410
+ "<|sep|>",
411
+ "<|nl|>",
412
+ "<|mask|>",
413
+ "<|...|>",
414
+ "<|cont|>",
415
+ "<|truncated|>",
416
+ "<|redacted|>"
417
+ ],
418
+ "is_local": false,
419
+ "model_max_length": 131072,
420
+ "pad_token": "<|pad|>",
421
+ "split_special_tokens": false,
422
+ "tokenizer_class": "Qwen2Tokenizer",
423
+ "unk_token": null
424
+ }
video_encoder.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa3a72612cd56cbc02329ce601ff15c55a6050ae2384d1db4e58563879a12b1
3
+ size 3402793248
video_generator.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5506b7b8cb74bd363d8618dd7524c28f8a0b8940763f8ea0cda93d0d8e1d8f14
3
+ size 94479052
vision_encoder.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97c435b54f83027950ff705c34e0e8d6e76cd6f6a23c51813c4151e6e02d2c20
3
+ size 2001005664
waveform_decoder.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d443fbe40c31e005a96f24ddda0da05ea1552807c0426e2cdc0d0d54f72f50f
3
+ size 69328680