Hugging Face's logo

TheHouseOfTheDude
/
INTELLECT-3_Compressed-Tensors

Text Generation
English
vllm
conversational
compressed-tensors
awq
w4a16
quantized
Mixture of Experts
Model card Files
xet
Community
phaedawg commited on
Commit
22d9515
·
verified ·
1 Parent(s): 1e3e123

Add files using upload-large-folder tool

Browse files
Files changed (32) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +137 -0
  3. config.json +225 -0
  4. generation_config.json +12 -0
  5. model-00001-of-00023.safetensors +3 -0
  6. model-00002-of-00023.safetensors +3 -0
  7. model-00003-of-00023.safetensors +3 -0
  8. model-00004-of-00023.safetensors +3 -0
  9. model-00005-of-00023.safetensors +3 -0
  10. model-00006-of-00023.safetensors +3 -0
  11. model-00007-of-00023.safetensors +3 -0
  12. model-00008-of-00023.safetensors +3 -0
  13. model-00009-of-00023.safetensors +3 -0
  14. model-00010-of-00023.safetensors +3 -0
  15. model-00011-of-00023.safetensors +3 -0
  16. model-00012-of-00023.safetensors +3 -0
  17. model-00013-of-00023.safetensors +3 -0
  18. model-00014-of-00023.safetensors +3 -0
  19. model-00015-of-00023.safetensors +3 -0
  20. model-00016-of-00023.safetensors +3 -0
  21. model-00017-of-00023.safetensors +3 -0
  22. model-00018-of-00023.safetensors +3 -0
  23. model-00019-of-00023.safetensors +3 -0
  24. model-00020-of-00023.safetensors +3 -0
  25. model-00021-of-00023.safetensors +3 -0
  26. model-00022-of-00023.safetensors +3 -0
  27. model-00023-of-00023.safetensors +3 -0
  28. model.safetensors.index.json +0 -0
  29. recipe.yaml +104 -0
  30. special_tokens_map.json +40 -0
  31. tokenizer.json +3 -0
  32. tokenizer_config.json +341 -0
.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 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% macro render_extra_keys(json_dict, handled_keys) %}
2
+ {%- if json_dict is mapping %}
3
+ {%- for json_key in json_dict if json_key not in handled_keys %}
4
+ {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
5
+ {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
6
+ {%- else %}
7
+ {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
8
+ {%- endif %}
9
+ {%- endfor %}
10
+ {%- endif %}
11
+ {% endmacro %}
12
+
13
+ {%- if messages[0]["role"] == "system" %}
14
+ {%- set system_message = messages[0]["content"] %}
15
+ {%- set loop_messages = messages[1:] %}
16
+ {%- else %}
17
+ {%- set loop_messages = messages %}
18
+ {%- endif %}
19
+
20
+ {%- if not tools is defined %}
21
+ {%- set tools = [] %}
22
+ {%- endif %}
23
+
24
+ {%- if system_message is defined %}
25
+ {{- "<|im_start|>system\n" + system_message }}
26
+ {%- else %}
27
+ {%- if tools is iterable and tools | length > 0 %}
28
+ {{- "<|im_start|>system\nYou are INTELLECT-3, a helpful assistant developed by Prime Intellect, that can interact with a computer to solve tasks." }}
29
+ {%- endif %}
30
+ {%- endif %}
31
+ {%- if tools is iterable and tools | length > 0 %}
32
+ {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
33
+ {{- "<tools>" }}
34
+ {%- for tool in tools %}
35
+ {%- if tool.function is defined %}
36
+ {%- set tool = tool.function %}
37
+ {%- endif %}
38
+ {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
39
+ {%- if tool.description is defined %}
40
+ {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
41
+ {%- endif %}
42
+ {{- '\n<parameters>' }}
43
+ {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
44
+ {%- for param_name, param_fields in tool.parameters.properties|items %}
45
+ {{- '\n<parameter>' }}
46
+ {{- '\n<name>' ~ param_name ~ '</name>' }}
47
+ {%- if param_fields.type is defined %}
48
+ {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
49
+ {%- endif %}
50
+ {%- if param_fields.description is defined %}
51
+ {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
52
+ {%- endif %}
53
+ {%- set handled_keys = ['name', 'type', 'description'] %}
54
+ {{- render_extra_keys(param_fields, handled_keys) }}
55
+ {{- '\n</parameter>' }}
56
+ {%- endfor %}
57
+ {%- endif %}
58
+ {% set handled_keys = ['type', 'properties'] %}
59
+ {{- render_extra_keys(tool.parameters, handled_keys) }}
60
+ {{- '\n</parameters>' }}
61
+ {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
62
+ {{- render_extra_keys(tool, handled_keys) }}
63
+ {{- '\n</function>' }}
64
+ {%- endfor %}
65
+ {{- "\n</tools>" }}
66
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
67
+ {%- endif %}
68
+ {%- if system_message is defined %}
69
+ {{- '<|im_end|>\n' }}
70
+ {%- else %}
71
+ {%- if tools is iterable and tools | length > 0 %}
72
+ {{- '<|im_end|>\n' }}
73
+ {%- endif %}
74
+ {%- endif %}
75
+ {%- for message in loop_messages %}
76
+ {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
77
+ {{- '<|im_start|>' + message.role }}
78
+ {%- if message.content is defined and message.content is string %}
79
+ {%- if message.reasoning_content is defined -%}
80
+ {%- if message.reasoning_content -%}
81
+ {{ '\n<think>' + message.reasoning_content.strip() + '</think>' }}
82
+ {%- else -%}
83
+ {{ '\n<think></think>' }}
84
+ {%- endif -%}
85
+ {%- endif -%}
86
+ {{- '\n' + message.content | trim + '\n' }}
87
+ {%- endif %}
88
+ {%- for tool_call in message.tool_calls %}
89
+ {%- if tool_call.function is defined %}
90
+ {%- set tool_call = tool_call.function %}
91
+ {%- endif %}
92
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
93
+ {%- if tool_call.arguments is defined %}
94
+ {%- for args_name, args_value in tool_call.arguments|items %}
95
+ {{- '<parameter=' + args_name + '>\n' }}
96
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
97
+ {{- args_value }}
98
+ {{- '\n</parameter>\n' }}
99
+ {%- endfor %}
100
+ {%- endif %}
101
+ {{- '</function>\n</tool_call>' }}
102
+ {%- endfor %}
103
+ {{- '<|im_end|>\n' }}
104
+ {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
105
+ {{- '<|im_start|>' + message.role }}
106
+ {%- if message.role == "assistant" and message.reasoning_content is defined %}
107
+ {%- if message.reasoning_content -%}
108
+ {{ '\n<think>' + message.reasoning_content.strip() + '</think>' }}
109
+ {%- else -%}
110
+ {{ '\n<think></think>' }}
111
+ {%- endif -%}
112
+ {%- if message.content.strip() -%}
113
+ {{ '\n' + message.content.strip() }}
114
+ {%- endif -%}
115
+ {%- else %}
116
+ {{- '\n' + message.content }}
117
+ {%- endif %}
118
+ {{- '<|im_end|>' + '\n' }}
119
+ {%- elif message.role == "tool" %}
120
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
121
+ {{- '<|im_start|>user\n' }}
122
+ {%- endif %}
123
+ {{- '<tool_response>\n' }}
124
+ {{- message.content }}
125
+ {{- '\n</tool_response>\n' }}
126
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
127
+ {{- '<|im_end|>\n' }}
128
+ {%- elif loop.last %}
129
+ {{- '<|im_end|>\n' }}
130
+ {%- endif %}
131
+ {%- else %}
132
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
133
+ {%- endif %}
134
+ {%- endfor %}
135
+ {%- if add_generation_prompt %}
136
+ {{- '<|im_start|>assistant\n<think>' }}
137
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,225 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Glm4MoeForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_glm4_moe.Glm4MoeConfig",
9
+ "AutoModel": "modeling_glm4_moe.Glm4MoeModel",
10
+ "AutoModelForCausalLM": "modeling_glm4_moe.Glm4MoeForCausalLM"
11
+ },
12
+ "dtype": "bfloat16",
13
+ "eos_token_id": [
14
+ 151334,
15
+ 151329
16
+ ],
17
+ "first_k_dense_replace": 1,
18
+ "head_dim": 128,
19
+ "hidden_act": "silu",
20
+ "hidden_size": 4096,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 10944,
23
+ "max_position_embeddings": 131072,
24
+ "model_type": "glm4_moe",
25
+ "moe_intermediate_size": 1408,
26
+ "n_group": 1,
27
+ "n_routed_experts": 128,
28
+ "n_shared_experts": 1,
29
+ "norm_topk_prob": true,
30
+ "num_attention_heads": 96,
31
+ "num_experts_per_tok": 8,
32
+ "num_hidden_layers": 46,
33
+ "num_key_value_heads": 8,
34
+ "num_nextn_predict_layers": 1,
35
+ "pad_token_id": 151329,
36
+ "partial_rotary_factor": 0.5,
37
+ "quantization_config": {
38
+ "config_groups": {
39
+ "group_0": {
40
+ "format": "pack-quantized",
41
+ "input_activations": null,
42
+ "output_activations": null,
43
+ "targets": [
44
+ "Linear"
45
+ ],
46
+ "weights": {
47
+ "actorder": null,
48
+ "block_structure": null,
49
+ "dynamic": false,
50
+ "group_size": 128,
51
+ "num_bits": 8,
52
+ "observer": "minmax",
53
+ "observer_kwargs": {},
54
+ "strategy": "group",
55
+ "symmetric": true,
56
+ "type": "int"
57
+ }
58
+ }
59
+ },
60
+ "format": "pack-quantized",
61
+ "global_compression_ratio": null,
62
+ "ignore": [
63
+ "model.layers.0.self_attn.q_proj",
64
+ "model.layers.0.self_attn.k_proj",
65
+ "model.layers.0.self_attn.v_proj",
66
+ "model.layers.0.self_attn.o_proj",
67
+ "model.layers.0.mlp.gate_proj",
68
+ "model.layers.0.mlp.up_proj",
69
+ "model.layers.0.mlp.down_proj",
70
+ "model.layers.1.mlp.shared_experts.gate_proj",
71
+ "model.layers.1.mlp.shared_experts.up_proj",
72
+ "model.layers.1.mlp.shared_experts.down_proj",
73
+ "model.layers.2.mlp.shared_experts.gate_proj",
74
+ "model.layers.2.mlp.shared_experts.up_proj",
75
+ "model.layers.2.mlp.shared_experts.down_proj",
76
+ "model.layers.3.mlp.shared_experts.gate_proj",
77
+ "model.layers.3.mlp.shared_experts.up_proj",
78
+ "model.layers.3.mlp.shared_experts.down_proj",
79
+ "model.layers.4.mlp.shared_experts.gate_proj",
80
+ "model.layers.4.mlp.shared_experts.up_proj",
81
+ "model.layers.4.mlp.shared_experts.down_proj",
82
+ "model.layers.5.mlp.shared_experts.gate_proj",
83
+ "model.layers.5.mlp.shared_experts.up_proj",
84
+ "model.layers.5.mlp.shared_experts.down_proj",
85
+ "model.layers.6.mlp.shared_experts.gate_proj",
86
+ "model.layers.6.mlp.shared_experts.up_proj",
87
+ "model.layers.6.mlp.shared_experts.down_proj",
88
+ "model.layers.7.mlp.shared_experts.gate_proj",
89
+ "model.layers.7.mlp.shared_experts.up_proj",
90
+ "model.layers.7.mlp.shared_experts.down_proj",
91
+ "model.layers.8.mlp.shared_experts.gate_proj",
92
+ "model.layers.8.mlp.shared_experts.up_proj",
93
+ "model.layers.8.mlp.shared_experts.down_proj",
94
+ "model.layers.9.mlp.shared_experts.gate_proj",
95
+ "model.layers.9.mlp.shared_experts.up_proj",
96
+ "model.layers.9.mlp.shared_experts.down_proj",
97
+ "model.layers.10.mlp.shared_experts.gate_proj",
98
+ "model.layers.10.mlp.shared_experts.up_proj",
99
+ "model.layers.10.mlp.shared_experts.down_proj",
100
+ "model.layers.11.mlp.shared_experts.gate_proj",
101
+ "model.layers.11.mlp.shared_experts.up_proj",
102
+ "model.layers.11.mlp.shared_experts.down_proj",
103
+ "model.layers.12.mlp.shared_experts.gate_proj",
104
+ "model.layers.12.mlp.shared_experts.up_proj",
105
+ "model.layers.12.mlp.shared_experts.down_proj",
106
+ "model.layers.13.mlp.shared_experts.gate_proj",
107
+ "model.layers.13.mlp.shared_experts.up_proj",
108
+ "model.layers.13.mlp.shared_experts.down_proj",
109
+ "model.layers.14.mlp.shared_experts.gate_proj",
110
+ "model.layers.14.mlp.shared_experts.up_proj",
111
+ "model.layers.14.mlp.shared_experts.down_proj",
112
+ "model.layers.15.mlp.shared_experts.gate_proj",
113
+ "model.layers.15.mlp.shared_experts.up_proj",
114
+ "model.layers.15.mlp.shared_experts.down_proj",
115
+ "model.layers.16.mlp.shared_experts.gate_proj",
116
+ "model.layers.16.mlp.shared_experts.up_proj",
117
+ "model.layers.16.mlp.shared_experts.down_proj",
118
+ "model.layers.17.mlp.shared_experts.gate_proj",
119
+ "model.layers.17.mlp.shared_experts.up_proj",
120
+ "model.layers.17.mlp.shared_experts.down_proj",
121
+ "model.layers.18.mlp.shared_experts.gate_proj",
122
+ "model.layers.18.mlp.shared_experts.up_proj",
123
+ "model.layers.18.mlp.shared_experts.down_proj",
124
+ "model.layers.19.mlp.shared_experts.gate_proj",
125
+ "model.layers.19.mlp.shared_experts.up_proj",
126
+ "model.layers.19.mlp.shared_experts.down_proj",
127
+ "model.layers.20.mlp.shared_experts.gate_proj",
128
+ "model.layers.20.mlp.shared_experts.up_proj",
129
+ "model.layers.20.mlp.shared_experts.down_proj",
130
+ "model.layers.21.mlp.shared_experts.gate_proj",
131
+ "model.layers.21.mlp.shared_experts.up_proj",
132
+ "model.layers.21.mlp.shared_experts.down_proj",
133
+ "model.layers.22.mlp.shared_experts.gate_proj",
134
+ "model.layers.22.mlp.shared_experts.up_proj",
135
+ "model.layers.22.mlp.shared_experts.down_proj",
136
+ "model.layers.23.mlp.shared_experts.gate_proj",
137
+ "model.layers.23.mlp.shared_experts.up_proj",
138
+ "model.layers.23.mlp.shared_experts.down_proj",
139
+ "model.layers.24.mlp.shared_experts.gate_proj",
140
+ "model.layers.24.mlp.shared_experts.up_proj",
141
+ "model.layers.24.mlp.shared_experts.down_proj",
142
+ "model.layers.25.mlp.shared_experts.gate_proj",
143
+ "model.layers.25.mlp.shared_experts.up_proj",
144
+ "model.layers.25.mlp.shared_experts.down_proj",
145
+ "model.layers.26.mlp.shared_experts.gate_proj",
146
+ "model.layers.26.mlp.shared_experts.up_proj",
147
+ "model.layers.26.mlp.shared_experts.down_proj",
148
+ "model.layers.27.mlp.shared_experts.gate_proj",
149
+ "model.layers.27.mlp.shared_experts.up_proj",
150
+ "model.layers.27.mlp.shared_experts.down_proj",
151
+ "model.layers.28.mlp.shared_experts.gate_proj",
152
+ "model.layers.28.mlp.shared_experts.up_proj",
153
+ "model.layers.28.mlp.shared_experts.down_proj",
154
+ "model.layers.29.mlp.shared_experts.gate_proj",
155
+ "model.layers.29.mlp.shared_experts.up_proj",
156
+ "model.layers.29.mlp.shared_experts.down_proj",
157
+ "model.layers.30.mlp.shared_experts.gate_proj",
158
+ "model.layers.30.mlp.shared_experts.up_proj",
159
+ "model.layers.30.mlp.shared_experts.down_proj",
160
+ "model.layers.31.mlp.shared_experts.gate_proj",
161
+ "model.layers.31.mlp.shared_experts.up_proj",
162
+ "model.layers.31.mlp.shared_experts.down_proj",
163
+ "model.layers.32.mlp.shared_experts.gate_proj",
164
+ "model.layers.32.mlp.shared_experts.up_proj",
165
+ "model.layers.32.mlp.shared_experts.down_proj",
166
+ "model.layers.33.mlp.shared_experts.gate_proj",
167
+ "model.layers.33.mlp.shared_experts.up_proj",
168
+ "model.layers.33.mlp.shared_experts.down_proj",
169
+ "model.layers.34.mlp.shared_experts.gate_proj",
170
+ "model.layers.34.mlp.shared_experts.up_proj",
171
+ "model.layers.34.mlp.shared_experts.down_proj",
172
+ "model.layers.35.mlp.shared_experts.gate_proj",
173
+ "model.layers.35.mlp.shared_experts.up_proj",
174
+ "model.layers.35.mlp.shared_experts.down_proj",
175
+ "model.layers.36.mlp.shared_experts.gate_proj",
176
+ "model.layers.36.mlp.shared_experts.up_proj",
177
+ "model.layers.36.mlp.shared_experts.down_proj",
178
+ "model.layers.37.mlp.shared_experts.gate_proj",
179
+ "model.layers.37.mlp.shared_experts.up_proj",
180
+ "model.layers.37.mlp.shared_experts.down_proj",
181
+ "model.layers.38.mlp.shared_experts.gate_proj",
182
+ "model.layers.38.mlp.shared_experts.up_proj",
183
+ "model.layers.38.mlp.shared_experts.down_proj",
184
+ "model.layers.39.mlp.shared_experts.gate_proj",
185
+ "model.layers.39.mlp.shared_experts.up_proj",
186
+ "model.layers.39.mlp.shared_experts.down_proj",
187
+ "model.layers.40.mlp.shared_experts.gate_proj",
188
+ "model.layers.40.mlp.shared_experts.up_proj",
189
+ "model.layers.40.mlp.shared_experts.down_proj",
190
+ "model.layers.41.mlp.shared_experts.gate_proj",
191
+ "model.layers.41.mlp.shared_experts.up_proj",
192
+ "model.layers.41.mlp.shared_experts.down_proj",
193
+ "model.layers.42.mlp.shared_experts.gate_proj",
194
+ "model.layers.42.mlp.shared_experts.up_proj",
195
+ "model.layers.42.mlp.shared_experts.down_proj",
196
+ "model.layers.43.mlp.shared_experts.gate_proj",
197
+ "model.layers.43.mlp.shared_experts.up_proj",
198
+ "model.layers.43.mlp.shared_experts.down_proj",
199
+ "model.layers.44.mlp.shared_experts.gate_proj",
200
+ "model.layers.44.mlp.shared_experts.up_proj",
201
+ "model.layers.44.mlp.shared_experts.down_proj",
202
+ "model.layers.45.mlp.shared_experts.gate_proj",
203
+ "model.layers.45.mlp.shared_experts.up_proj",
204
+ "model.layers.45.mlp.shared_experts.down_proj",
205
+ "lm_head"
206
+ ],
207
+ "kv_cache_scheme": null,
208
+ "quant_method": "compressed-tensors",
209
+ "quantization_status": "compressed",
210
+ "sparsity_config": {},
211
+ "transform_config": {},
212
+ "version": "0.12.2"
213
+ },
214
+ "rms_norm_eps": 1e-05,
215
+ "rope_scaling": null,
216
+ "rope_theta": 1000000,
217
+ "routed_scaling_factor": 1.0,
218
+ "tie_word_embeddings": false,
219
+ "topk_group": 1,
220
+ "transformers_version": "4.56.2",
221
+ "use_cache": false,
222
+ "use_grouped_mm": true,
223
+ "use_qk_norm": false,
224
+ "vocab_size": 151552
225
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151334,
6
+ 151329
7
+ ],
8
+ "pad_token_id": 151329,
9
+ "temperature": 0.6,
10
+ "transformers_version": "4.56.2",
11
+ "use_cache": false
12
+ }
model-00001-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce403e62501c4d13720620f62f17eee927ee8e1515017481b13ca6c832cbeaee
3
+ size 4996704808
model-00002-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9159ac3c56b43b47369483ab228ed0bf55cb1fbfdc652eab7d68d20f976f7e82
3
+ size 4996615352
model-00003-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c00e31b624ab1c71cd50ea00999328f933ec4b3e342696eb71d7e93b0a657a65
3
+ size 4996615352
model-00004-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40f2b3c526c7accedffe9e49841d376a16fc931b67b6de49411146d858ababcb
3
+ size 4996615352
model-00005-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0068c6b4aaa2c2a835dbaf065c5a5d92f8ddf4849383fe76367063e23ece4ee
3
+ size 4996616176
model-00006-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6e4b5fa909db25aa8fbb9f07a8797eea68e52a19598a113e59b5d45b3827a12
3
+ size 4996617816
model-00007-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37c2c660c122e60c241c7a6677c7455f66f5da6e67df450e73bab5171e23378c
3
+ size 4996617912
model-00008-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dceebb4f9cb25ea2fa56d5dc09c25c4bf0601af03a89fca6b978bf52ffd07d9
3
+ size 4996617912
model-00009-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:516da9b528c5a1cab89a30f51d351a1e99e25a05e283489f908c03537661b410
3
+ size 4996631744
model-00010-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aead072ed68482121edffd690fca84ed9ebad84abb0de2e79b1f6ea83d0fcaa5
3
+ size 4996617720
model-00011-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:255b1abde9c5ad2003e5cb67e0d9f32b5c67f225fa1c62ca41b665963c9f1649
3
+ size 4996617800
model-00012-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99574cd759694f68dbf2c8f2d0b38d148e9e5dfc76a9bab8ef18528ab1a6995e
3
+ size 4996617808
model-00013-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29c1b980be6f4ba29881b75f948d582802758462cc161ac502880aa6515e58ec
3
+ size 4996617800
model-00014-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540bb896c0b92c9bfbcd24bb9544d53ebd1e4d4c15c0dd7afa2f81b55c1a2379
3
+ size 4996617800
model-00015-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43149a243f68544ce3c1f03587b86d0c243e834807689f5f6c81d5eefa5b75ce
3
+ size 4996617808
model-00016-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be0c7fe6ad7881d37e0ce1fa3bf1fcf292dc725fb573f7e72142acbadd859bde
3
+ size 4996617800
model-00017-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a03390bb7b3342d0bfc59faa71c909f0b9c14daff0b8846ff70344a88c4fffc
3
+ size 4996617800
model-00018-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e0034de32a47b66a28b98e089b0ce579f592dcb4096e3c7abb811c63056b39c
3
+ size 4996617856
model-00019-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fcf366579bdad49dcaa40cb9d8c081d665c5e094084c186307c3b64b9843b57
3
+ size 4996617912
model-00020-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d362b9751b647f2df33a217e2da2de0265019b5a9dae9fd3c21d2db6824d9d99
3
+ size 4997486208
model-00021-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f7b491f0371b1440ae8e03d83aea3cdd434964c7f495fc7e7dd07b1d84f0b6d
3
+ size 4995763376
model-00022-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d0edc3568a762dfd26bf589e89ae350d39869363328a7d6afd054d36f1638d4
3
+ size 4610529248
model-00023-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a01b48b1170ac6c907f09fb10744ed45ecc815e52642d155cdcdbd374f1ee833
3
+ size 1241514112
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
recipe.yaml ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ AWQModifier:
4
+ config_groups:
5
+ group_0:
6
+ targets: [Linear]
7
+ weights:
8
+ num_bits: 8
9
+ type: int
10
+ symmetric: true
11
+ group_size: 128
12
+ strategy: group
13
+ block_structure: null
14
+ dynamic: false
15
+ actorder: null
16
+ observer: minmax
17
+ observer_kwargs: {}
18
+ input_activations: null
19
+ output_activations: null
20
+ format: null
21
+ targets: [Linear]
22
+ ignore: [model.layers.0.self_attn.q_proj, model.layers.0.self_attn.k_proj, model.layers.0.self_attn.v_proj,
23
+ model.layers.0.self_attn.o_proj, model.layers.0.mlp.gate_proj, model.layers.0.mlp.up_proj,
24
+ model.layers.0.mlp.down_proj, model.layers.1.mlp.shared_experts.gate_proj, model.layers.1.mlp.shared_experts.up_proj,
25
+ model.layers.1.mlp.shared_experts.down_proj, model.layers.2.mlp.shared_experts.gate_proj,
26
+ model.layers.2.mlp.shared_experts.up_proj, model.layers.2.mlp.shared_experts.down_proj,
27
+ model.layers.3.mlp.shared_experts.gate_proj, model.layers.3.mlp.shared_experts.up_proj,
28
+ model.layers.3.mlp.shared_experts.down_proj, model.layers.4.mlp.shared_experts.gate_proj,
29
+ model.layers.4.mlp.shared_experts.up_proj, model.layers.4.mlp.shared_experts.down_proj,
30
+ model.layers.5.mlp.shared_experts.gate_proj, model.layers.5.mlp.shared_experts.up_proj,
31
+ model.layers.5.mlp.shared_experts.down_proj, model.layers.6.mlp.shared_experts.gate_proj,
32
+ model.layers.6.mlp.shared_experts.up_proj, model.layers.6.mlp.shared_experts.down_proj,
33
+ model.layers.7.mlp.shared_experts.gate_proj, model.layers.7.mlp.shared_experts.up_proj,
34
+ model.layers.7.mlp.shared_experts.down_proj, model.layers.8.mlp.shared_experts.gate_proj,
35
+ model.layers.8.mlp.shared_experts.up_proj, model.layers.8.mlp.shared_experts.down_proj,
36
+ model.layers.9.mlp.shared_experts.gate_proj, model.layers.9.mlp.shared_experts.up_proj,
37
+ model.layers.9.mlp.shared_experts.down_proj, model.layers.10.mlp.shared_experts.gate_proj,
38
+ model.layers.10.mlp.shared_experts.up_proj, model.layers.10.mlp.shared_experts.down_proj,
39
+ model.layers.11.mlp.shared_experts.gate_proj, model.layers.11.mlp.shared_experts.up_proj,
40
+ model.layers.11.mlp.shared_experts.down_proj, model.layers.12.mlp.shared_experts.gate_proj,
41
+ model.layers.12.mlp.shared_experts.up_proj, model.layers.12.mlp.shared_experts.down_proj,
42
+ model.layers.13.mlp.shared_experts.gate_proj, model.layers.13.mlp.shared_experts.up_proj,
43
+ model.layers.13.mlp.shared_experts.down_proj, model.layers.14.mlp.shared_experts.gate_proj,
44
+ model.layers.14.mlp.shared_experts.up_proj, model.layers.14.mlp.shared_experts.down_proj,
45
+ model.layers.15.mlp.shared_experts.gate_proj, model.layers.15.mlp.shared_experts.up_proj,
46
+ model.layers.15.mlp.shared_experts.down_proj, model.layers.16.mlp.shared_experts.gate_proj,
47
+ model.layers.16.mlp.shared_experts.up_proj, model.layers.16.mlp.shared_experts.down_proj,
48
+ model.layers.17.mlp.shared_experts.gate_proj, model.layers.17.mlp.shared_experts.up_proj,
49
+ model.layers.17.mlp.shared_experts.down_proj, model.layers.18.mlp.shared_experts.gate_proj,
50
+ model.layers.18.mlp.shared_experts.up_proj, model.layers.18.mlp.shared_experts.down_proj,
51
+ model.layers.19.mlp.shared_experts.gate_proj, model.layers.19.mlp.shared_experts.up_proj,
52
+ model.layers.19.mlp.shared_experts.down_proj, model.layers.20.mlp.shared_experts.gate_proj,
53
+ model.layers.20.mlp.shared_experts.up_proj, model.layers.20.mlp.shared_experts.down_proj,
54
+ model.layers.21.mlp.shared_experts.gate_proj, model.layers.21.mlp.shared_experts.up_proj,
55
+ model.layers.21.mlp.shared_experts.down_proj, model.layers.22.mlp.shared_experts.gate_proj,
56
+ model.layers.22.mlp.shared_experts.up_proj, model.layers.22.mlp.shared_experts.down_proj,
57
+ model.layers.23.mlp.shared_experts.gate_proj, model.layers.23.mlp.shared_experts.up_proj,
58
+ model.layers.23.mlp.shared_experts.down_proj, model.layers.24.mlp.shared_experts.gate_proj,
59
+ model.layers.24.mlp.shared_experts.up_proj, model.layers.24.mlp.shared_experts.down_proj,
60
+ model.layers.25.mlp.shared_experts.gate_proj, model.layers.25.mlp.shared_experts.up_proj,
61
+ model.layers.25.mlp.shared_experts.down_proj, model.layers.26.mlp.shared_experts.gate_proj,
62
+ model.layers.26.mlp.shared_experts.up_proj, model.layers.26.mlp.shared_experts.down_proj,
63
+ model.layers.27.mlp.shared_experts.gate_proj, model.layers.27.mlp.shared_experts.up_proj,
64
+ model.layers.27.mlp.shared_experts.down_proj, model.layers.28.mlp.shared_experts.gate_proj,
65
+ model.layers.28.mlp.shared_experts.up_proj, model.layers.28.mlp.shared_experts.down_proj,
66
+ model.layers.29.mlp.shared_experts.gate_proj, model.layers.29.mlp.shared_experts.up_proj,
67
+ model.layers.29.mlp.shared_experts.down_proj, model.layers.30.mlp.shared_experts.gate_proj,
68
+ model.layers.30.mlp.shared_experts.up_proj, model.layers.30.mlp.shared_experts.down_proj,
69
+ model.layers.31.mlp.shared_experts.gate_proj, model.layers.31.mlp.shared_experts.up_proj,
70
+ model.layers.31.mlp.shared_experts.down_proj, model.layers.32.mlp.shared_experts.gate_proj,
71
+ model.layers.32.mlp.shared_experts.up_proj, model.layers.32.mlp.shared_experts.down_proj,
72
+ model.layers.33.mlp.shared_experts.gate_proj, model.layers.33.mlp.shared_experts.up_proj,
73
+ model.layers.33.mlp.shared_experts.down_proj, model.layers.34.mlp.shared_experts.gate_proj,
74
+ model.layers.34.mlp.shared_experts.up_proj, model.layers.34.mlp.shared_experts.down_proj,
75
+ model.layers.35.mlp.shared_experts.gate_proj, model.layers.35.mlp.shared_experts.up_proj,
76
+ model.layers.35.mlp.shared_experts.down_proj, model.layers.36.mlp.shared_experts.gate_proj,
77
+ model.layers.36.mlp.shared_experts.up_proj, model.layers.36.mlp.shared_experts.down_proj,
78
+ model.layers.37.mlp.shared_experts.gate_proj, model.layers.37.mlp.shared_experts.up_proj,
79
+ model.layers.37.mlp.shared_experts.down_proj, model.layers.38.mlp.shared_experts.gate_proj,
80
+ model.layers.38.mlp.shared_experts.up_proj, model.layers.38.mlp.shared_experts.down_proj,
81
+ model.layers.39.mlp.shared_experts.gate_proj, model.layers.39.mlp.shared_experts.up_proj,
82
+ model.layers.39.mlp.shared_experts.down_proj, model.layers.40.mlp.shared_experts.gate_proj,
83
+ model.layers.40.mlp.shared_experts.up_proj, model.layers.40.mlp.shared_experts.down_proj,
84
+ model.layers.41.mlp.shared_experts.gate_proj, model.layers.41.mlp.shared_experts.up_proj,
85
+ model.layers.41.mlp.shared_experts.down_proj, model.layers.42.mlp.shared_experts.gate_proj,
86
+ model.layers.42.mlp.shared_experts.up_proj, model.layers.42.mlp.shared_experts.down_proj,
87
+ model.layers.43.mlp.shared_experts.gate_proj, model.layers.43.mlp.shared_experts.up_proj,
88
+ model.layers.43.mlp.shared_experts.down_proj, model.layers.44.mlp.shared_experts.gate_proj,
89
+ model.layers.44.mlp.shared_experts.up_proj, model.layers.44.mlp.shared_experts.down_proj,
90
+ model.layers.45.mlp.shared_experts.gate_proj, model.layers.45.mlp.shared_experts.up_proj,
91
+ model.layers.45.mlp.shared_experts.down_proj, model.layers.46.self_attn.q_proj, model.layers.46.self_attn.k_proj,
92
+ model.layers.46.self_attn.v_proj, model.layers.46.self_attn.o_proj, model.layers.46.mlp.shared_experts.gate_proj,
93
+ model.layers.46.mlp.shared_experts.up_proj, model.layers.46.mlp.shared_experts.down_proj,
94
+ lm_head]
95
+ mappings:
96
+ - smooth_layer: re:.*input_layernorm$
97
+ balance_layers: ['re:.*q_proj$', 're:.*k_proj$', 're:.*v_proj$']
98
+ - smooth_layer: re:.*v_proj$
99
+ balance_layers: ['re:.*o_proj$']
100
+ - smooth_layer: re:.*post_attention_layernorm$
101
+ balance_layers: ['re:.*gate_proj$', 're:.*up_proj$']
102
+ - smooth_layer: re:.*up_proj$
103
+ balance_layers: ['re:.*down_proj$']
104
+ duo_scaling: true
special_tokens_map.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "[MASK]",
5
+ "[gMASK]",
6
+ "[sMASK]",
7
+ "<sop>",
8
+ "<eop>",
9
+ "<|system|>",
10
+ "<|user|>",
11
+ "<|assistant|>",
12
+ "<|observation|>",
13
+ "<|begin_of_image|>",
14
+ "<|end_of_image|>",
15
+ "<|begin_of_video|>",
16
+ "<|end_of_video|>",
17
+ "<|begin_of_audio|>",
18
+ "<|end_of_audio|>",
19
+ "<|begin_of_transcription|>",
20
+ "<|end_of_transcription|>",
21
+ "<|code_prefix|>",
22
+ "<|code_middle|>",
23
+ "<|code_suffix|>",
24
+ "/nothink"
25
+ ],
26
+ "eos_token": {
27
+ "content": "<|im_end|>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "pad_token": {
34
+ "content": "<|endoftext|>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:840a2be2f18847f07571118fb785c9bde4726991852229d98469e421bf5d1064
3
+ size 19971076
tokenizer_config.json ADDED
@@ -0,0 +1,341 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "151329": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "151330": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "151331": {
20
+ "content": "[gMASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "151332": {
28
+ "content": "[sMASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "151333": {
36
+ "content": "<|im_start|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "151334": {
44
+ "content": "<|im_end|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "151335": {
52
+ "content": "<|system|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "151336": {
60
+ "content": "<|user|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "151337": {
68
+ "content": "<|assistant|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "151338": {
76
+ "content": "<|observation|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "151339": {
84
+ "content": "<|begin_of_image|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "151340": {
92
+ "content": "<|end_of_image|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "151341": {
100
+ "content": "<|begin_of_video|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "151342": {
108
+ "content": "<|end_of_video|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "151343": {
116
+ "content": "<|begin_of_audio|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "151344": {
124
+ "content": "<|end_of_audio|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "151345": {
132
+ "content": "<|begin_of_transcription|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "151346": {
140
+ "content": "<|end_of_transcription|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "151347": {
148
+ "content": "<|code_prefix|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "151348": {
156
+ "content": "<|code_middle|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "151349": {
164
+ "content": "<|code_suffix|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "151350": {
172
+ "content": "<think>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "151351": {
180
+ "content": "</think>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "151352": {
188
+ "content": "<tool_call>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "151353": {
196
+ "content": "</tool_call>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "151354": {
204
+ "content": "<tool_response>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "151355": {
212
+ "content": "</tool_response>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "151356": {
220
+ "content": "<arg_key>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "151357": {
228
+ "content": "</arg_key>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "151358": {
236
+ "content": "<arg_value>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "151359": {
244
+ "content": "</arg_value>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "151360": {
252
+ "content": "/nothink",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "151361": {
260
+ "content": "<|begin_of_box|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "151362": {
268
+ "content": "<|end_of_box|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "151363": {
276
+ "content": "<|image|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "151364": {
284
+ "content": "<|video|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "151365": {
292
+ "content": "<sop>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "151366": {
300
+ "content": "<eop>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ }
307
+ },
308
+ "additional_special_tokens": [
309
+ "<|endoftext|>",
310
+ "[MASK]",
311
+ "[gMASK]",
312
+ "[sMASK]",
313
+ "<sop>",
314
+ "<eop>",
315
+ "<|system|>",
316
+ "<|user|>",
317
+ "<|assistant|>",
318
+ "<|observation|>",
319
+ "<|begin_of_image|>",
320
+ "<|end_of_image|>",
321
+ "<|begin_of_video|>",
322
+ "<|end_of_video|>",
323
+ "<|begin_of_audio|>",
324
+ "<|end_of_audio|>",
325
+ "<|begin_of_transcription|>",
326
+ "<|end_of_transcription|>",
327
+ "<|code_prefix|>",
328
+ "<|code_middle|>",
329
+ "<|code_suffix|>",
330
+ "/nothink"
331
+ ],
332
+ "clean_up_tokenization_spaces": false,
333
+ "do_lower_case": false,
334
+ "eos_token": "<|im_end|>",
335
+ "extra_special_tokens": {},
336
+ "model_max_length": 128000,
337
+ "pad_token": "<|endoftext|>",
338
+ "padding_side": "left",
339
+ "remove_space": false,
340
+ "tokenizer_class": "PreTrainedTokenizerFast"
341
+ }