aurick commited on
Commit
d19f843
·
verified ·
1 Parent(s): 681c6c9

Upload Inkling-Small-NVFP4 model

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
chat_template.jinja ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set effort_map = {"none": 0.0, "minimal": 0.1, "low": 0.2, "medium": 0.7, "high": 0.9, "max": 0.99} -%}
2
+ {%- set role_token = {"user": "<|message_user|>", "assistant": "<|message_model|>", "system": "<|message_system|>", "tool": "<|message_tool|>"} -%}
3
+
4
+ {%- macro emit_thinking_effort() -%}
5
+ {%- set eff = reasoning_effort if reasoning_effort is defined and reasoning_effort is not none else 0.9 -%}
6
+ {%- if eff is string -%}
7
+ {%- set key = eff | trim -%}
8
+ {%- if key not in effort_map -%}
9
+ {{- raise_exception("Unknown reasoning_effort: " ~ eff) -}}
10
+ {%- endif -%}
11
+ {%- set num = effort_map[key] -%}
12
+ {%- else -%}
13
+ {%- set num = eff | float -%}
14
+ {%- endif -%}
15
+ {%- if num < 0.0 or num > 0.99 -%}
16
+ {{- raise_exception("reasoning_effort must be in [0.0, 0.99]") -}}
17
+ {%- endif -%}
18
+ {{- "<|message_system|><|content_text|>Thinking effort level: " -}}
19
+ {%- if num == 0.0 -%}0{%- else -%}{{ num }}{%- endif -%}
20
+ {{- "<|end_message|>" -}}
21
+ {%- endmacro -%}
22
+
23
+ {%- if tools -%}
24
+ {%- set tool_state = namespace(specs=[]) -%}
25
+ {%- for tool in tools -%}
26
+ {%- set fn = tool.function if tool.function is defined else tool -%}
27
+ {%- set spec = {
28
+ "description": (fn.description if fn.description is defined and fn.description else ""),
29
+ "name": fn.name,
30
+ "parameters": (fn.parameters if fn.parameters is defined and fn.parameters else {}),
31
+ "type": (tool.type if tool.type is defined and tool.type else "function"),
32
+ } -%}
33
+ {%- set tool_state.specs = tool_state.specs + [spec] -%}
34
+ {%- endfor -%}
35
+ {{- "<|message_system|>tool_declare<|content_xml|>" -}}
36
+ {{- tool_state.specs | tojson(sort_keys=true, separators=(",", ":")) -}}
37
+ {{- "<|end_message|>" -}}
38
+ {%- endif -%}
39
+
40
+ {%- set state = namespace(effort_emitted=false) -%}
41
+ {%- for message in messages -%}
42
+ {%- if message.role not in role_token -%}
43
+ {{- raise_exception("Unknown message role: " ~ message.role) -}}
44
+ {%- endif -%}
45
+ {%- if not state.effort_emitted and message.role != "system" -%}
46
+ {{- emit_thinking_effort() -}}
47
+ {%- set state.effort_emitted = true -%}
48
+ {%- endif -%}
49
+
50
+ {%- set rtok = role_token[message.role] -%}
51
+
52
+ {%- if message.role == "tool" -%}
53
+ {%- set tool_name_state = namespace(name="") -%}
54
+ {%- if message.name is defined and message.name -%}
55
+ {%- set tool_name_state.name = message.name -%}
56
+ {%- elif message.tool_call_id is defined and message.tool_call_id -%}
57
+ {%- for prev in messages -%}
58
+ {%- if prev.role == "assistant" and prev.tool_calls -%}
59
+ {%- for tc in prev.tool_calls -%}
60
+ {%- if tc.id is defined and tc.id == message.tool_call_id and tc.function.name is defined -%}
61
+ {%- set tool_name_state.name = tc.function.name -%}
62
+ {%- endif -%}
63
+ {%- endfor -%}
64
+ {%- endif -%}
65
+ {%- endfor -%}
66
+ {%- endif -%}
67
+ {{- rtok -}}
68
+ {%- if tool_name_state.name -%}{{- tool_name_state.name -}}{%- endif -%}
69
+ {{- "<|content_text|>" -}}
70
+ {%- if message.content is string -%}{{- message.content -}}{%- endif -%}
71
+ {{- "<|end_message|>" -}}
72
+
73
+ {%- else -%}
74
+ {%- if message.role == "assistant" and message.reasoning_content is defined and message.reasoning_content -%}
75
+ {{- "<|message_model|><|content_thinking|>" ~ message.reasoning_content ~ "<|end_message|>" -}}
76
+ {%- endif -%}
77
+
78
+ {%- if message.content is string -%}
79
+ {{- rtok ~ "<|content_text|>" ~ message.content ~ "<|end_message|>" -}}
80
+ {%- elif message.content -%}
81
+ {%- for part in message.content -%}
82
+ {%- if part is string -%}
83
+ {{- rtok ~ "<|content_text|>" ~ part ~ "<|end_message|>" -}}
84
+ {%- elif part.type is not defined or part.type in ("text", "input_text") -%}
85
+ {%- set text_part = (part.text if part.text is defined and part.text is string else "") -%}
86
+ {{- rtok ~ "<|content_text|>" ~ text_part ~ "<|end_message|>" -}}
87
+ {%- elif part.type in ("image", "input_image", "image_url") -%}
88
+ {{- rtok ~ "<|content_image|><|unused_200054|><|end_message|>" -}}
89
+ {%- elif part.type in ("audio", "input_audio", "audio_url") -%}
90
+ {{- rtok ~ "<|content_audio_input|><|unused_200053|><|audio_end|><|end_message|>" -}}
91
+ {%- else -%}
92
+ {{- raise_exception("Unsupported content part type: " ~ part.type) -}}
93
+ {%- endif -%}
94
+ {%- endfor -%}
95
+ {%- endif -%}
96
+
97
+ {%- if message.role == "assistant" and message.tool_calls -%}
98
+ {%- for tc in message.tool_calls -%}
99
+ {%- set fn = tc.function -%}
100
+ {%- if fn.name is not defined or fn.name is not string -%}
101
+ {{- raise_exception("tool call function name must be a string") -}}
102
+ {%- endif -%}
103
+ {%- set args = fn.arguments if fn.arguments is defined and fn.arguments else {} -%}
104
+ {%- if args is string -%}
105
+ {{- raise_exception("tool call arguments must be a parsed object, not a JSON string; canonicalize upstream") -}}
106
+ {%- endif -%}
107
+ {%- if args is not mapping -%}
108
+ {{- raise_exception("tool call arguments must be an object") -}}
109
+ {%- endif -%}
110
+ {{- "<|message_model|>" ~ fn.name ~ "<|content_invoke_tool_json|>" -}}
111
+ {{- '{"name":' ~ (fn.name | tojson(sort_keys=true, separators=(",", ":"))) ~ ',"args":' -}}
112
+ {{- (args | tojson(sort_keys=true, separators=(",", ":"))) -}}
113
+ {{- "}<|end_message|>" -}}
114
+ {%- endfor -%}
115
+ {%- endif -%}
116
+
117
+ {%- if message.role == "assistant" -%}
118
+ {{- "<|content_model_end_sampling|>" -}}
119
+ {%- endif -%}
120
+ {%- endif -%}
121
+ {%- endfor -%}
122
+
123
+ {%- if not state.effort_emitted -%}
124
+ {{- emit_thinking_effort() -}}
125
+ {%- endif -%}
126
+
127
+ {%- if add_generation_prompt -%}
128
+ {{- "<|message_model|>" -}}
129
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "InklingForConditionalGeneration"
4
+ ],
5
+ "model_type": "inkling_mm_model",
6
+ "eos_token_id": 200006,
7
+ "text_config": {
8
+ "model_max_length": 1048576,
9
+ "torch_dtype": "bfloat16",
10
+ "hidden_size": 4096,
11
+ "num_hidden_layers": 42,
12
+ "vocab_size": 201024,
13
+ "num_attention_heads": 32,
14
+ "num_key_value_heads": 8,
15
+ "head_dim": 128,
16
+ "d_rel": 16,
17
+ "rel_extent": 1024,
18
+ "q_bias": false,
19
+ "o_bias": false,
20
+ "log_scaling_n_floor": 128000,
21
+ "log_scaling_alpha": 0.1,
22
+ "rms_norm_eps": 1e-06,
23
+ "use_embed_norm": true,
24
+ "local_layer_ids": [
25
+ 0,
26
+ 1,
27
+ 2,
28
+ 3,
29
+ 4,
30
+ 6,
31
+ 7,
32
+ 8,
33
+ 9,
34
+ 10,
35
+ 12,
36
+ 13,
37
+ 14,
38
+ 15,
39
+ 16,
40
+ 18,
41
+ 19,
42
+ 20,
43
+ 21,
44
+ 22,
45
+ 24,
46
+ 25,
47
+ 26,
48
+ 27,
49
+ 28,
50
+ 30,
51
+ 31,
52
+ 32,
53
+ 33,
54
+ 34,
55
+ 36,
56
+ 37,
57
+ 38,
58
+ 39,
59
+ 40
60
+ ],
61
+ "dense_mlp_idx": 2,
62
+ "use_sconv": true,
63
+ "sconv_kernel_size": 4,
64
+ "unpadded_vocab_size": 200058,
65
+ "logits_mup_width_multiplier": 16.0,
66
+ "final_logit_softcapping": null,
67
+ "swa_head_dim": 128,
68
+ "swa_num_attention_heads": 32,
69
+ "swa_num_key_value_heads": 8,
70
+ "sliding_window_size": 512,
71
+ "n_routed_experts": 256,
72
+ "num_experts_per_tok": 6,
73
+ "n_shared_experts": 2,
74
+ "shared_expert_sink": true,
75
+ "dense_intermediate_size": 16384,
76
+ "intermediate_size": 2048,
77
+ "route_scale": 8.0,
78
+ "use_gate_bias": true,
79
+ "gate_activation": "sigmoid",
80
+ "norm_after_topk": true,
81
+ "use_global_scale": true
82
+ },
83
+ "audio_config": {
84
+ "decoder_dmodel": 4096,
85
+ "n_mel_bins": 80,
86
+ "mel_vocab_size": 16,
87
+ "bias": false,
88
+ "dmel_min_value": -7.0,
89
+ "dmel_max_value": 2.0,
90
+ "use_audio_norm": true,
91
+ "audio_mode": "dmel"
92
+ },
93
+ "vision_config": {
94
+ "vision_encoder_type": "hmlp",
95
+ "decoder_dmodel": 4096,
96
+ "patch_size": 40,
97
+ "temporal_patch_size": 2,
98
+ "n_channels": 3,
99
+ "n_layers": 4,
100
+ "use_vision_norm": true
101
+ },
102
+ "mtp_config": {
103
+ "num_nextn_predict_layers": 8,
104
+ "chain_hidden_post_norm": false,
105
+ "local_layer_ids": [
106
+ 0,
107
+ 2,
108
+ 4,
109
+ 5,
110
+ 6,
111
+ 7
112
+ ]
113
+ }
114
+ }
hf_quant_config.json ADDED
@@ -0,0 +1,411 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "quantization": {
3
+ "quant_algo": "NVFP4",
4
+ "kv_cache_quant_algo": "none",
5
+ "exclude_modules": [
6
+ "model.audio.decoder",
7
+ "model.audio.encoder",
8
+ "model.audio.final_norm",
9
+ "model.llm.embed",
10
+ "model.llm.embed_norm",
11
+ "model.llm.norm",
12
+ "model.llm.unembed",
13
+ "model.visual.final_norm",
14
+ "model.visual.layers.linear_0",
15
+ "model.visual.layers.linear_1",
16
+ "model.visual.layers.linear_2",
17
+ "model.visual.layers.linear_3",
18
+ "model.visual.layers.norm_0",
19
+ "model.visual.layers.norm_1",
20
+ "model.visual.layers.norm_2",
21
+ "model.llm.layers.0.attn",
22
+ "model.llm.layers.0.attn_norm",
23
+ "model.llm.layers.0.attn_sconv",
24
+ "model.llm.layers.0.mlp.global_scale",
25
+ "model.llm.layers.0.mlp.w13_dn",
26
+ "model.llm.layers.0.mlp.w2_md",
27
+ "model.llm.layers.0.mlp_norm",
28
+ "model.llm.layers.0.mlp_sconv",
29
+ "model.llm.layers.1.attn",
30
+ "model.llm.layers.1.attn_norm",
31
+ "model.llm.layers.1.attn_sconv",
32
+ "model.llm.layers.1.mlp.global_scale",
33
+ "model.llm.layers.1.mlp.w13_dn",
34
+ "model.llm.layers.1.mlp.w2_md",
35
+ "model.llm.layers.1.mlp_norm",
36
+ "model.llm.layers.1.mlp_sconv",
37
+ "model.llm.layers.10.attn",
38
+ "model.llm.layers.10.attn_norm",
39
+ "model.llm.layers.10.attn_sconv",
40
+ "model.llm.layers.10.mlp.gate",
41
+ "model.llm.layers.10.mlp.shared_experts",
42
+ "model.llm.layers.10.mlp_norm",
43
+ "model.llm.layers.10.mlp_sconv",
44
+ "model.llm.layers.11.attn",
45
+ "model.llm.layers.11.attn_norm",
46
+ "model.llm.layers.11.attn_sconv",
47
+ "model.llm.layers.11.mlp.gate",
48
+ "model.llm.layers.11.mlp.shared_experts",
49
+ "model.llm.layers.11.mlp_norm",
50
+ "model.llm.layers.11.mlp_sconv",
51
+ "model.llm.layers.12.attn",
52
+ "model.llm.layers.12.attn_norm",
53
+ "model.llm.layers.12.attn_sconv",
54
+ "model.llm.layers.12.mlp.gate",
55
+ "model.llm.layers.12.mlp.shared_experts",
56
+ "model.llm.layers.12.mlp_norm",
57
+ "model.llm.layers.12.mlp_sconv",
58
+ "model.llm.layers.13.attn",
59
+ "model.llm.layers.13.attn_norm",
60
+ "model.llm.layers.13.attn_sconv",
61
+ "model.llm.layers.13.mlp.gate",
62
+ "model.llm.layers.13.mlp.shared_experts",
63
+ "model.llm.layers.13.mlp_norm",
64
+ "model.llm.layers.13.mlp_sconv",
65
+ "model.llm.layers.14.attn",
66
+ "model.llm.layers.14.attn_norm",
67
+ "model.llm.layers.14.attn_sconv",
68
+ "model.llm.layers.14.mlp.gate",
69
+ "model.llm.layers.14.mlp.shared_experts",
70
+ "model.llm.layers.14.mlp_norm",
71
+ "model.llm.layers.14.mlp_sconv",
72
+ "model.llm.layers.15.attn",
73
+ "model.llm.layers.15.attn_norm",
74
+ "model.llm.layers.15.attn_sconv",
75
+ "model.llm.layers.15.mlp.gate",
76
+ "model.llm.layers.15.mlp.shared_experts",
77
+ "model.llm.layers.15.mlp_norm",
78
+ "model.llm.layers.15.mlp_sconv",
79
+ "model.llm.layers.16.attn",
80
+ "model.llm.layers.16.attn_norm",
81
+ "model.llm.layers.16.attn_sconv",
82
+ "model.llm.layers.16.mlp.gate",
83
+ "model.llm.layers.16.mlp.shared_experts",
84
+ "model.llm.layers.16.mlp_norm",
85
+ "model.llm.layers.16.mlp_sconv",
86
+ "model.llm.layers.17.attn",
87
+ "model.llm.layers.17.attn_norm",
88
+ "model.llm.layers.17.attn_sconv",
89
+ "model.llm.layers.17.mlp.gate",
90
+ "model.llm.layers.17.mlp.shared_experts",
91
+ "model.llm.layers.17.mlp_norm",
92
+ "model.llm.layers.17.mlp_sconv",
93
+ "model.llm.layers.18.attn",
94
+ "model.llm.layers.18.attn_norm",
95
+ "model.llm.layers.18.attn_sconv",
96
+ "model.llm.layers.18.mlp.gate",
97
+ "model.llm.layers.18.mlp.shared_experts",
98
+ "model.llm.layers.18.mlp_norm",
99
+ "model.llm.layers.18.mlp_sconv",
100
+ "model.llm.layers.19.attn",
101
+ "model.llm.layers.19.attn_norm",
102
+ "model.llm.layers.19.attn_sconv",
103
+ "model.llm.layers.19.mlp.gate",
104
+ "model.llm.layers.19.mlp.shared_experts",
105
+ "model.llm.layers.19.mlp_norm",
106
+ "model.llm.layers.19.mlp_sconv",
107
+ "model.llm.layers.2.attn",
108
+ "model.llm.layers.2.attn_norm",
109
+ "model.llm.layers.2.attn_sconv",
110
+ "model.llm.layers.2.mlp.experts",
111
+ "model.llm.layers.2.mlp.gate",
112
+ "model.llm.layers.2.mlp.shared_experts",
113
+ "model.llm.layers.2.mlp_norm",
114
+ "model.llm.layers.2.mlp_sconv",
115
+ "model.llm.layers.20.attn",
116
+ "model.llm.layers.20.attn_norm",
117
+ "model.llm.layers.20.attn_sconv",
118
+ "model.llm.layers.20.mlp.gate",
119
+ "model.llm.layers.20.mlp.shared_experts",
120
+ "model.llm.layers.20.mlp_norm",
121
+ "model.llm.layers.20.mlp_sconv",
122
+ "model.llm.layers.21.attn",
123
+ "model.llm.layers.21.attn_norm",
124
+ "model.llm.layers.21.attn_sconv",
125
+ "model.llm.layers.21.mlp.gate",
126
+ "model.llm.layers.21.mlp.shared_experts",
127
+ "model.llm.layers.21.mlp_norm",
128
+ "model.llm.layers.21.mlp_sconv",
129
+ "model.llm.layers.22.attn",
130
+ "model.llm.layers.22.attn_norm",
131
+ "model.llm.layers.22.attn_sconv",
132
+ "model.llm.layers.22.mlp.gate",
133
+ "model.llm.layers.22.mlp.shared_experts",
134
+ "model.llm.layers.22.mlp_norm",
135
+ "model.llm.layers.22.mlp_sconv",
136
+ "model.llm.layers.23.attn",
137
+ "model.llm.layers.23.attn_norm",
138
+ "model.llm.layers.23.attn_sconv",
139
+ "model.llm.layers.23.mlp.gate",
140
+ "model.llm.layers.23.mlp.shared_experts",
141
+ "model.llm.layers.23.mlp_norm",
142
+ "model.llm.layers.23.mlp_sconv",
143
+ "model.llm.layers.24.attn",
144
+ "model.llm.layers.24.attn_norm",
145
+ "model.llm.layers.24.attn_sconv",
146
+ "model.llm.layers.24.mlp.gate",
147
+ "model.llm.layers.24.mlp.shared_experts",
148
+ "model.llm.layers.24.mlp_norm",
149
+ "model.llm.layers.24.mlp_sconv",
150
+ "model.llm.layers.25.attn",
151
+ "model.llm.layers.25.attn_norm",
152
+ "model.llm.layers.25.attn_sconv",
153
+ "model.llm.layers.25.mlp.gate",
154
+ "model.llm.layers.25.mlp.shared_experts",
155
+ "model.llm.layers.25.mlp_norm",
156
+ "model.llm.layers.25.mlp_sconv",
157
+ "model.llm.layers.26.attn",
158
+ "model.llm.layers.26.attn_norm",
159
+ "model.llm.layers.26.attn_sconv",
160
+ "model.llm.layers.26.mlp.gate",
161
+ "model.llm.layers.26.mlp.shared_experts",
162
+ "model.llm.layers.26.mlp_norm",
163
+ "model.llm.layers.26.mlp_sconv",
164
+ "model.llm.layers.27.attn",
165
+ "model.llm.layers.27.attn_norm",
166
+ "model.llm.layers.27.attn_sconv",
167
+ "model.llm.layers.27.mlp.gate",
168
+ "model.llm.layers.27.mlp.shared_experts",
169
+ "model.llm.layers.27.mlp_norm",
170
+ "model.llm.layers.27.mlp_sconv",
171
+ "model.llm.layers.28.attn",
172
+ "model.llm.layers.28.attn_norm",
173
+ "model.llm.layers.28.attn_sconv",
174
+ "model.llm.layers.28.mlp.gate",
175
+ "model.llm.layers.28.mlp.shared_experts",
176
+ "model.llm.layers.28.mlp_norm",
177
+ "model.llm.layers.28.mlp_sconv",
178
+ "model.llm.layers.29.attn",
179
+ "model.llm.layers.29.attn_norm",
180
+ "model.llm.layers.29.attn_sconv",
181
+ "model.llm.layers.29.mlp.gate",
182
+ "model.llm.layers.29.mlp.shared_experts",
183
+ "model.llm.layers.29.mlp_norm",
184
+ "model.llm.layers.29.mlp_sconv",
185
+ "model.llm.layers.3.attn",
186
+ "model.llm.layers.3.attn_norm",
187
+ "model.llm.layers.3.attn_sconv",
188
+ "model.llm.layers.3.mlp.gate",
189
+ "model.llm.layers.3.mlp.shared_experts",
190
+ "model.llm.layers.3.mlp_norm",
191
+ "model.llm.layers.3.mlp_sconv",
192
+ "model.llm.layers.30.attn",
193
+ "model.llm.layers.30.attn_norm",
194
+ "model.llm.layers.30.attn_sconv",
195
+ "model.llm.layers.30.mlp.gate",
196
+ "model.llm.layers.30.mlp.shared_experts",
197
+ "model.llm.layers.30.mlp_norm",
198
+ "model.llm.layers.30.mlp_sconv",
199
+ "model.llm.layers.31.attn",
200
+ "model.llm.layers.31.attn_norm",
201
+ "model.llm.layers.31.attn_sconv",
202
+ "model.llm.layers.31.mlp.gate",
203
+ "model.llm.layers.31.mlp.shared_experts",
204
+ "model.llm.layers.31.mlp_norm",
205
+ "model.llm.layers.31.mlp_sconv",
206
+ "model.llm.layers.32.attn",
207
+ "model.llm.layers.32.attn_norm",
208
+ "model.llm.layers.32.attn_sconv",
209
+ "model.llm.layers.32.mlp.gate",
210
+ "model.llm.layers.32.mlp.shared_experts",
211
+ "model.llm.layers.32.mlp_norm",
212
+ "model.llm.layers.32.mlp_sconv",
213
+ "model.llm.layers.33.attn",
214
+ "model.llm.layers.33.attn_norm",
215
+ "model.llm.layers.33.attn_sconv",
216
+ "model.llm.layers.33.mlp.gate",
217
+ "model.llm.layers.33.mlp.shared_experts",
218
+ "model.llm.layers.33.mlp_norm",
219
+ "model.llm.layers.33.mlp_sconv",
220
+ "model.llm.layers.34.attn",
221
+ "model.llm.layers.34.attn_norm",
222
+ "model.llm.layers.34.attn_sconv",
223
+ "model.llm.layers.34.mlp.gate",
224
+ "model.llm.layers.34.mlp.shared_experts",
225
+ "model.llm.layers.34.mlp_norm",
226
+ "model.llm.layers.34.mlp_sconv",
227
+ "model.llm.layers.35.attn",
228
+ "model.llm.layers.35.attn_norm",
229
+ "model.llm.layers.35.attn_sconv",
230
+ "model.llm.layers.35.mlp.gate",
231
+ "model.llm.layers.35.mlp.shared_experts",
232
+ "model.llm.layers.35.mlp_norm",
233
+ "model.llm.layers.35.mlp_sconv",
234
+ "model.llm.layers.36.attn",
235
+ "model.llm.layers.36.attn_norm",
236
+ "model.llm.layers.36.attn_sconv",
237
+ "model.llm.layers.36.mlp.gate",
238
+ "model.llm.layers.36.mlp.shared_experts",
239
+ "model.llm.layers.36.mlp_norm",
240
+ "model.llm.layers.36.mlp_sconv",
241
+ "model.llm.layers.37.attn",
242
+ "model.llm.layers.37.attn_norm",
243
+ "model.llm.layers.37.attn_sconv",
244
+ "model.llm.layers.37.mlp.gate",
245
+ "model.llm.layers.37.mlp.shared_experts",
246
+ "model.llm.layers.37.mlp_norm",
247
+ "model.llm.layers.37.mlp_sconv",
248
+ "model.llm.layers.38.attn",
249
+ "model.llm.layers.38.attn_norm",
250
+ "model.llm.layers.38.attn_sconv",
251
+ "model.llm.layers.38.mlp.gate",
252
+ "model.llm.layers.38.mlp.shared_experts",
253
+ "model.llm.layers.38.mlp_norm",
254
+ "model.llm.layers.38.mlp_sconv",
255
+ "model.llm.layers.39.attn",
256
+ "model.llm.layers.39.attn_norm",
257
+ "model.llm.layers.39.attn_sconv",
258
+ "model.llm.layers.39.mlp.gate",
259
+ "model.llm.layers.39.mlp.shared_experts",
260
+ "model.llm.layers.39.mlp_norm",
261
+ "model.llm.layers.39.mlp_sconv",
262
+ "model.llm.layers.4.attn",
263
+ "model.llm.layers.4.attn_norm",
264
+ "model.llm.layers.4.attn_sconv",
265
+ "model.llm.layers.4.mlp.gate",
266
+ "model.llm.layers.4.mlp.shared_experts",
267
+ "model.llm.layers.4.mlp_norm",
268
+ "model.llm.layers.4.mlp_sconv",
269
+ "model.llm.layers.40.attn",
270
+ "model.llm.layers.40.attn_norm",
271
+ "model.llm.layers.40.attn_sconv",
272
+ "model.llm.layers.40.mlp.gate",
273
+ "model.llm.layers.40.mlp.shared_experts",
274
+ "model.llm.layers.40.mlp_norm",
275
+ "model.llm.layers.40.mlp_sconv",
276
+ "model.llm.layers.41.attn",
277
+ "model.llm.layers.41.attn_norm",
278
+ "model.llm.layers.41.attn_sconv",
279
+ "model.llm.layers.41.mlp.gate",
280
+ "model.llm.layers.41.mlp.shared_experts",
281
+ "model.llm.layers.41.mlp_norm",
282
+ "model.llm.layers.41.mlp_sconv",
283
+ "model.llm.layers.5.attn",
284
+ "model.llm.layers.5.attn_norm",
285
+ "model.llm.layers.5.attn_sconv",
286
+ "model.llm.layers.5.mlp.gate",
287
+ "model.llm.layers.5.mlp.shared_experts",
288
+ "model.llm.layers.5.mlp_norm",
289
+ "model.llm.layers.5.mlp_sconv",
290
+ "model.llm.layers.6.attn",
291
+ "model.llm.layers.6.attn_norm",
292
+ "model.llm.layers.6.attn_sconv",
293
+ "model.llm.layers.6.mlp.gate",
294
+ "model.llm.layers.6.mlp.shared_experts",
295
+ "model.llm.layers.6.mlp_norm",
296
+ "model.llm.layers.6.mlp_sconv",
297
+ "model.llm.layers.7.attn",
298
+ "model.llm.layers.7.attn_norm",
299
+ "model.llm.layers.7.attn_sconv",
300
+ "model.llm.layers.7.mlp.gate",
301
+ "model.llm.layers.7.mlp.shared_experts",
302
+ "model.llm.layers.7.mlp_norm",
303
+ "model.llm.layers.7.mlp_sconv",
304
+ "model.llm.layers.8.attn",
305
+ "model.llm.layers.8.attn_norm",
306
+ "model.llm.layers.8.attn_sconv",
307
+ "model.llm.layers.8.mlp.gate",
308
+ "model.llm.layers.8.mlp.shared_experts",
309
+ "model.llm.layers.8.mlp_norm",
310
+ "model.llm.layers.8.mlp_sconv",
311
+ "model.llm.layers.9.attn",
312
+ "model.llm.layers.9.attn_norm",
313
+ "model.llm.layers.9.attn_sconv",
314
+ "model.llm.layers.9.mlp.gate",
315
+ "model.llm.layers.9.mlp.shared_experts",
316
+ "model.llm.layers.9.mlp_norm",
317
+ "model.llm.layers.9.mlp_sconv"
318
+ ],
319
+ "modelopt_quant_config": {
320
+ "quant_cfg": {
321
+ "*weight_quantizer": {
322
+ "num_bits": [
323
+ 2,
324
+ 1
325
+ ],
326
+ "block_sizes": {
327
+ "-1": 16,
328
+ "type": "dynamic",
329
+ "scale_bits": [
330
+ 4,
331
+ 3
332
+ ]
333
+ },
334
+ "axis": null,
335
+ "enable": true
336
+ },
337
+ "*input_quantizer": {
338
+ "num_bits": [
339
+ 2,
340
+ 1
341
+ ],
342
+ "block_sizes": {
343
+ "-1": 16,
344
+ "type": "dynamic",
345
+ "scale_bits": [
346
+ 4,
347
+ 3
348
+ ]
349
+ },
350
+ "axis": null,
351
+ "enable": true
352
+ },
353
+ "nn.BatchNorm1d": {
354
+ "*": {
355
+ "enable": false
356
+ }
357
+ },
358
+ "nn.BatchNorm2d": {
359
+ "*": {
360
+ "enable": false
361
+ }
362
+ },
363
+ "nn.BatchNorm3d": {
364
+ "*": {
365
+ "enable": false
366
+ }
367
+ },
368
+ "nn.LeakyReLU": {
369
+ "*": {
370
+ "enable": false
371
+ }
372
+ },
373
+ "*lm_head*": {
374
+ "enable": false
375
+ },
376
+ "*proj_out.*": {
377
+ "enable": false
378
+ },
379
+ "*block_sparse_moe.gate*": {
380
+ "enable": false
381
+ },
382
+ "*router*": {
383
+ "enable": false
384
+ },
385
+ "*mlp.gate.*": {
386
+ "enable": false
387
+ },
388
+ "*mlp.shared_expert_gate.*": {
389
+ "enable": false
390
+ },
391
+ "*linear_attn.conv1d*": {
392
+ "enable": false
393
+ },
394
+ "*mixer.conv1d*": {
395
+ "enable": false
396
+ },
397
+ "*output_layer*": {
398
+ "enable": false
399
+ },
400
+ "output.*": {
401
+ "enable": false
402
+ },
403
+ "default": {
404
+ "enable": false
405
+ }
406
+ },
407
+ "algorithm": "max"
408
+ },
409
+ "group_size": 16
410
+ }
411
+ }
model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0536fc0774c061f006fbc0f8062300b80f7fa3c6395753f9558a53231ccdfdaf
3
+ size 19797851172
model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94046cd4c60e9f8b84e646af29b48d972b16328ef16c68e1d224e7cc1c108f69
3
+ size 18832947622
model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b011d77adab48cfedab8d82da3ee45e9658a298b5a2efe79386c9f80be83c90
3
+ size 19460482192
model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84efa4eab97da5d95e42813cd40a682439cfbd6cbdc9e644cc2aed650034b66
3
+ size 19886208500
model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04911920af137efb2bac5a8a3c65b1cd727b1c8f0a6ddcc691534c52e5cb3dce
3
+ size 19970085622
model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f2e9eb03063a3cdbc9361fd7f203d213476d7ca3295fe45757e2fe1f26513a8
3
+ size 18910731870
model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:728792823d6ba5b214503a3d75d39bbd239ba129a40b34ddb67f6d93e03fc0df
3
+ size 15485561834
model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc821c24f1af8342e02a456f06315c8c6c1e374d2060e258864117a660fbf37e
3
+ size 19791451186
model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c91d957b4a0cf277822f4174a5bc6071eec51b0c7243f53069c6f3e3bb8a93fb
3
+ size 14134068242
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
mtp.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d286dd21cb982a0052d24ee0077ec6fc38f5a766dc6953e6c4b85c6473bfa7b3
3
+ size 4463845392
processor_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_token": "<|unused_200053|>",
3
+ "audio_bos_token": "<|content_audio_input|>",
4
+ "dmel_max_value": 2.0,
5
+ "dmel_min_value": -7.0,
6
+ "feature_extractor": {
7
+ "audio_token_duration_s": 0.05,
8
+ "feature_extractor_type": "InklingFeatureExtractor",
9
+ "feature_size": 80,
10
+ "hop_length": 800,
11
+ "n_fft": 1600,
12
+ "padding_side": "right",
13
+ "padding_value": 0.0,
14
+ "return_attention_mask": true,
15
+ "sampling_rate": 16000,
16
+ "window_size": 1600,
17
+ "window_size_multiplier": 2.0
18
+ },
19
+ "image_processor": {
20
+ "do_convert_rgb": true,
21
+ "do_normalize": true,
22
+ "do_rescale": true,
23
+ "do_resize": true,
24
+ "image_mean": [
25
+ 0.48145466,
26
+ 0.4578275,
27
+ 0.40821073
28
+ ],
29
+ "image_processor_type": "InklingImageProcessor",
30
+ "image_std": [
31
+ 0.26862954,
32
+ 0.26130258,
33
+ 0.27577711
34
+ ],
35
+ "resample": 3,
36
+ "rescale_factor": 0.00392156862745098,
37
+ "size": {
38
+ "height": 40,
39
+ "width": 40
40
+ }
41
+ },
42
+ "image_token": "<|unused_200054|>",
43
+ "image_bos_token": "<|content_image|>",
44
+ "num_dmel_bins": 16,
45
+ "processor_class": "InklingProcessor"
46
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|message_user|>",
5
+ "<|message_model|>",
6
+ "<|message_system|>",
7
+ "<|message_tool|>",
8
+ "<|content_text|>",
9
+ "<|content_image|>",
10
+ "<|content_model_end_sampling|>",
11
+ "<|content_thinking|>",
12
+ "<|end_message|>",
13
+ "<|content_audio_input|>",
14
+ "<|content_tool_error|>",
15
+ "<|audio|>",
16
+ "<|content_xml|>",
17
+ "<|begin_of_text|>",
18
+ "<|audio_end|>",
19
+ "<|content_invoke_tool_json|>",
20
+ "<|content_invoke_tool_text|>"
21
+ ]
22
+ }
tiktoken/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc253fd2b702f7a6da7105eaa8f3463b2f1247e83614f23e5323b921088bed2a
3
+ size 3615874
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fb6333a7db8fe5da90728e741e4a3ee4ac2ae12c5dd4958cc6f31688787d3c2
3
+ size 27875797
tokenizer_config.json ADDED
@@ -0,0 +1,508 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "199998": {
4
+ "content": "<|unused|>",
5
+ "single_word": false,
6
+ "lstrip": false,
7
+ "rstrip": false,
8
+ "normalized": false,
9
+ "special": true
10
+ },
11
+ "199999": {
12
+ "content": "<|endoftext|>",
13
+ "single_word": false,
14
+ "lstrip": false,
15
+ "rstrip": false,
16
+ "normalized": false,
17
+ "special": true
18
+ },
19
+ "200000": {
20
+ "content": "<|message_user|>",
21
+ "single_word": false,
22
+ "lstrip": false,
23
+ "rstrip": false,
24
+ "normalized": false,
25
+ "special": true
26
+ },
27
+ "200001": {
28
+ "content": "<|message_model|>",
29
+ "single_word": false,
30
+ "lstrip": false,
31
+ "rstrip": false,
32
+ "normalized": false,
33
+ "special": true
34
+ },
35
+ "200002": {
36
+ "content": "<|message_system|>",
37
+ "single_word": false,
38
+ "lstrip": false,
39
+ "rstrip": false,
40
+ "normalized": false,
41
+ "special": true
42
+ },
43
+ "200003": {
44
+ "content": "<|message_tool|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ "200004": {
52
+ "content": "<|content_text|>",
53
+ "single_word": false,
54
+ "lstrip": false,
55
+ "rstrip": false,
56
+ "normalized": false,
57
+ "special": true
58
+ },
59
+ "200005": {
60
+ "content": "<|content_image|>",
61
+ "single_word": false,
62
+ "lstrip": false,
63
+ "rstrip": false,
64
+ "normalized": false,
65
+ "special": true
66
+ },
67
+ "200006": {
68
+ "content": "<|content_model_end_sampling|>",
69
+ "single_word": false,
70
+ "lstrip": false,
71
+ "rstrip": false,
72
+ "normalized": false,
73
+ "special": true
74
+ },
75
+ "200007": {
76
+ "content": "<|unused_200007|>",
77
+ "single_word": false,
78
+ "lstrip": false,
79
+ "rstrip": false,
80
+ "normalized": false,
81
+ "special": true
82
+ },
83
+ "200008": {
84
+ "content": "<|content_thinking|>",
85
+ "single_word": false,
86
+ "lstrip": false,
87
+ "rstrip": false,
88
+ "normalized": false,
89
+ "special": true
90
+ },
91
+ "200009": {
92
+ "content": "<|unused_200009|>",
93
+ "single_word": false,
94
+ "lstrip": false,
95
+ "rstrip": false,
96
+ "normalized": false,
97
+ "special": true
98
+ },
99
+ "200010": {
100
+ "content": "<|end_message|>",
101
+ "single_word": false,
102
+ "lstrip": false,
103
+ "rstrip": false,
104
+ "normalized": false,
105
+ "special": true
106
+ },
107
+ "200011": {
108
+ "content": "<|unused_200011|>",
109
+ "single_word": false,
110
+ "lstrip": false,
111
+ "rstrip": false,
112
+ "normalized": false,
113
+ "special": true
114
+ },
115
+ "200012": {
116
+ "content": "<|unused_200012|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ "200013": {
124
+ "content": "<|unused_200013|>",
125
+ "single_word": false,
126
+ "lstrip": false,
127
+ "rstrip": false,
128
+ "normalized": false,
129
+ "special": true
130
+ },
131
+ "200014": {
132
+ "content": "<|unused_200014|>",
133
+ "single_word": false,
134
+ "lstrip": false,
135
+ "rstrip": false,
136
+ "normalized": false,
137
+ "special": true
138
+ },
139
+ "200015": {
140
+ "content": "<|unused_200015|>",
141
+ "single_word": false,
142
+ "lstrip": false,
143
+ "rstrip": false,
144
+ "normalized": false,
145
+ "special": true
146
+ },
147
+ "200016": {
148
+ "content": "<|unused_200016|>",
149
+ "single_word": false,
150
+ "lstrip": false,
151
+ "rstrip": false,
152
+ "normalized": false,
153
+ "special": true
154
+ },
155
+ "200017": {
156
+ "content": "<|unused_200017|>",
157
+ "single_word": false,
158
+ "lstrip": false,
159
+ "rstrip": false,
160
+ "normalized": false,
161
+ "special": true
162
+ },
163
+ "200018": {
164
+ "content": "<|unused_200018|>",
165
+ "single_word": false,
166
+ "lstrip": false,
167
+ "rstrip": false,
168
+ "normalized": false,
169
+ "special": true
170
+ },
171
+ "200019": {
172
+ "content": "<|unused_200019|>",
173
+ "single_word": false,
174
+ "lstrip": false,
175
+ "rstrip": false,
176
+ "normalized": false,
177
+ "special": true
178
+ },
179
+ "200020": {
180
+ "content": "<|content_audio_input|>",
181
+ "single_word": false,
182
+ "lstrip": false,
183
+ "rstrip": false,
184
+ "normalized": false,
185
+ "special": true
186
+ },
187
+ "200021": {
188
+ "content": "<|unused_200021|>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ "200022": {
196
+ "content": "<|content_tool_error|>",
197
+ "single_word": false,
198
+ "lstrip": false,
199
+ "rstrip": false,
200
+ "normalized": false,
201
+ "special": true
202
+ },
203
+ "200023": {
204
+ "content": "<|audio|>",
205
+ "single_word": false,
206
+ "lstrip": false,
207
+ "rstrip": false,
208
+ "normalized": false,
209
+ "special": true
210
+ },
211
+ "200024": {
212
+ "content": "<|content_xml|>",
213
+ "single_word": false,
214
+ "lstrip": false,
215
+ "rstrip": false,
216
+ "normalized": false,
217
+ "special": true
218
+ },
219
+ "200025": {
220
+ "content": "<|unused_200025|>",
221
+ "single_word": false,
222
+ "lstrip": false,
223
+ "rstrip": false,
224
+ "normalized": false,
225
+ "special": true
226
+ },
227
+ "200026": {
228
+ "content": "<|unused_200026|>",
229
+ "single_word": false,
230
+ "lstrip": false,
231
+ "rstrip": false,
232
+ "normalized": false,
233
+ "special": true
234
+ },
235
+ "200027": {
236
+ "content": "<|unused_200027|>",
237
+ "single_word": false,
238
+ "lstrip": false,
239
+ "rstrip": false,
240
+ "normalized": false,
241
+ "special": true
242
+ },
243
+ "200028": {
244
+ "content": "<|begin_of_text|>",
245
+ "single_word": false,
246
+ "lstrip": false,
247
+ "rstrip": false,
248
+ "normalized": false,
249
+ "special": true
250
+ },
251
+ "200029": {
252
+ "content": "<|unused_200029|>",
253
+ "single_word": false,
254
+ "lstrip": false,
255
+ "rstrip": false,
256
+ "normalized": false,
257
+ "special": true
258
+ },
259
+ "200030": {
260
+ "content": "<|unused_200030|>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ "200031": {
268
+ "content": "<|unused_200031|>",
269
+ "single_word": false,
270
+ "lstrip": false,
271
+ "rstrip": false,
272
+ "normalized": false,
273
+ "special": true
274
+ },
275
+ "200032": {
276
+ "content": "<|unused_200032|>",
277
+ "single_word": false,
278
+ "lstrip": false,
279
+ "rstrip": false,
280
+ "normalized": false,
281
+ "special": true
282
+ },
283
+ "200033": {
284
+ "content": "<|unused_200033|>",
285
+ "single_word": false,
286
+ "lstrip": false,
287
+ "rstrip": false,
288
+ "normalized": false,
289
+ "special": true
290
+ },
291
+ "200034": {
292
+ "content": "<|unused_200034|>",
293
+ "single_word": false,
294
+ "lstrip": false,
295
+ "rstrip": false,
296
+ "normalized": false,
297
+ "special": true
298
+ },
299
+ "200035": {
300
+ "content": "<|unused_200035|>",
301
+ "single_word": false,
302
+ "lstrip": false,
303
+ "rstrip": false,
304
+ "normalized": false,
305
+ "special": true
306
+ },
307
+ "200036": {
308
+ "content": "<|unused_200036|>",
309
+ "single_word": false,
310
+ "lstrip": false,
311
+ "rstrip": false,
312
+ "normalized": false,
313
+ "special": true
314
+ },
315
+ "200037": {
316
+ "content": "<|unused_200037|>",
317
+ "single_word": false,
318
+ "lstrip": false,
319
+ "rstrip": false,
320
+ "normalized": false,
321
+ "special": true
322
+ },
323
+ "200038": {
324
+ "content": "<|unused_200038|>",
325
+ "single_word": false,
326
+ "lstrip": false,
327
+ "rstrip": false,
328
+ "normalized": false,
329
+ "special": true
330
+ },
331
+ "200039": {
332
+ "content": "<|unused_200039|>",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ "200040": {
340
+ "content": "<|unused_200040|>",
341
+ "single_word": false,
342
+ "lstrip": false,
343
+ "rstrip": false,
344
+ "normalized": false,
345
+ "special": true
346
+ },
347
+ "200041": {
348
+ "content": "<|unused_200041|>",
349
+ "single_word": false,
350
+ "lstrip": false,
351
+ "rstrip": false,
352
+ "normalized": false,
353
+ "special": true
354
+ },
355
+ "200042": {
356
+ "content": "<|unused_200042|>",
357
+ "single_word": false,
358
+ "lstrip": false,
359
+ "rstrip": false,
360
+ "normalized": false,
361
+ "special": true
362
+ },
363
+ "200043": {
364
+ "content": "<|audio_end|>",
365
+ "single_word": false,
366
+ "lstrip": false,
367
+ "rstrip": false,
368
+ "normalized": false,
369
+ "special": true
370
+ },
371
+ "200044": {
372
+ "content": "<|unused_200044|>",
373
+ "single_word": false,
374
+ "lstrip": false,
375
+ "rstrip": false,
376
+ "normalized": false,
377
+ "special": true
378
+ },
379
+ "200045": {
380
+ "content": "<|unused_200045|>",
381
+ "single_word": false,
382
+ "lstrip": false,
383
+ "rstrip": false,
384
+ "normalized": false,
385
+ "special": true
386
+ },
387
+ "200046": {
388
+ "content": "<|unused_200046|>",
389
+ "single_word": false,
390
+ "lstrip": false,
391
+ "rstrip": false,
392
+ "normalized": false,
393
+ "special": true
394
+ },
395
+ "200047": {
396
+ "content": "<|unused_200047|>",
397
+ "single_word": false,
398
+ "lstrip": false,
399
+ "rstrip": false,
400
+ "normalized": false,
401
+ "special": true
402
+ },
403
+ "200048": {
404
+ "content": "<|unused_200048|>",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ "200049": {
412
+ "content": "<|content_invoke_tool_json|>",
413
+ "single_word": false,
414
+ "lstrip": false,
415
+ "rstrip": false,
416
+ "normalized": false,
417
+ "special": true
418
+ },
419
+ "200050": {
420
+ "content": "<|unused_200050|>",
421
+ "single_word": false,
422
+ "lstrip": false,
423
+ "rstrip": false,
424
+ "normalized": false,
425
+ "special": true
426
+ },
427
+ "200051": {
428
+ "content": "<|unused_200051|>",
429
+ "single_word": false,
430
+ "lstrip": false,
431
+ "rstrip": false,
432
+ "normalized": false,
433
+ "special": true
434
+ },
435
+ "200052": {
436
+ "content": "<|unused_200052|>",
437
+ "single_word": false,
438
+ "lstrip": false,
439
+ "rstrip": false,
440
+ "normalized": false,
441
+ "special": true
442
+ },
443
+ "200053": {
444
+ "content": "<|unused_200053|>",
445
+ "single_word": false,
446
+ "lstrip": false,
447
+ "rstrip": false,
448
+ "normalized": false,
449
+ "special": true
450
+ },
451
+ "200054": {
452
+ "content": "<|unused_200054|>",
453
+ "single_word": false,
454
+ "lstrip": false,
455
+ "rstrip": false,
456
+ "normalized": false,
457
+ "special": true
458
+ },
459
+ "200055": {
460
+ "content": "<|unused_200055|>",
461
+ "single_word": false,
462
+ "lstrip": false,
463
+ "rstrip": false,
464
+ "normalized": false,
465
+ "special": true
466
+ },
467
+ "200056": {
468
+ "content": "<|unused_200056|>",
469
+ "single_word": false,
470
+ "lstrip": false,
471
+ "rstrip": false,
472
+ "normalized": false,
473
+ "special": true
474
+ },
475
+ "200057": {
476
+ "content": "<|content_invoke_tool_text|>",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": false,
481
+ "special": true
482
+ }
483
+ },
484
+ "clean_up_tokenization_spaces": false,
485
+ "fix_mistral_regex": false,
486
+ "extra_special_tokens": {
487
+ "endoftext": "<|endoftext|>",
488
+ "message_user": "<|message_user|>",
489
+ "message_model": "<|message_model|>",
490
+ "message_system": "<|message_system|>",
491
+ "message_tool": "<|message_tool|>",
492
+ "content_text": "<|content_text|>",
493
+ "content_image": "<|content_image|>",
494
+ "content_model_end_sampling": "<|content_model_end_sampling|>",
495
+ "content_thinking": "<|content_thinking|>",
496
+ "end_message": "<|end_message|>",
497
+ "content_audio_input": "<|content_audio_input|>",
498
+ "content_tool_error": "<|content_tool_error|>",
499
+ "audio": "<|audio|>",
500
+ "content_xml": "<|content_xml|>",
501
+ "begin_of_text": "<|begin_of_text|>",
502
+ "audio_end": "<|audio_end|>",
503
+ "content_invoke_tool_json": "<|content_invoke_tool_json|>",
504
+ "content_invoke_tool_text": "<|content_invoke_tool_text|>"
505
+ },
506
+ "model_max_length": 1000000000000000019884624838656,
507
+ "tokenizer_class": "PreTrainedTokenizerFast"
508
+ }