Hugging Face's logo

txn545
/
Qwen3-Coder-Next-NVFP4

Safetensors
qwen3_next
modelopt
Model card Files
xet
Community
txn545 commited on
Commit
85a12a4
·
verified ·
1 Parent(s): d08d913

Add files using upload-large-folder tool

Browse files
Files changed (22) hide show
  1. .gitattributes +2 -0
  2. added_tokens.json +28 -0
  3. chat_template.jinja +117 -0
  4. config.json +369 -0
  5. generation_config.json +13 -0
  6. hf_quant_config.json +254 -0
  7. merges.txt +0 -0
  8. model-00001-of-00010.safetensors +3 -0
  9. model-00002-of-00010.safetensors +3 -0
  10. model-00003-of-00010.safetensors +3 -0
  11. model-00004-of-00010.safetensors +3 -0
  12. model-00005-of-00010.safetensors +3 -0
  13. model-00006-of-00010.safetensors +3 -0
  14. model-00007-of-00010.safetensors +3 -0
  15. model-00008-of-00010.safetensors +3 -0
  16. model-00009-of-00010.safetensors +3 -0
  17. model-00010-of-00010.safetensors +3 -0
  18. model.safetensors.index.json +3 -0
  19. special_tokens_map.json +25 -0
  20. tokenizer.json +3 -0
  21. tokenizer_config.json +239 -0
  22. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
37
+ model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 string %}
5
+ {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
6
+ {%- else %}
7
+ {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ 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 Qwen, a helpful AI assistant 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 and message.content | trim | length > 0 %}
79
+ {{- '\n' + message.content | trim + '\n' }}
80
+ {%- endif %}
81
+ {%- for tool_call in message.tool_calls %}
82
+ {%- if tool_call.function is defined %}
83
+ {%- set tool_call = tool_call.function %}
84
+ {%- endif %}
85
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
86
+ {%- if tool_call.arguments is defined %}
87
+ {%- for args_name, args_value in tool_call.arguments|items %}
88
+ {{- '<parameter=' + args_name + '>\n' }}
89
+ {%- set args_value = args_value if args_value is string else args_value | tojson | safe %}
90
+ {{- args_value }}
91
+ {{- '\n</parameter>\n' }}
92
+ {%- endfor %}
93
+ {%- endif %}
94
+ {{- '</function>\n</tool_call>' }}
95
+ {%- endfor %}
96
+ {{- '<|im_end|>\n' }}
97
+ {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
98
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
99
+ {%- elif message.role == "tool" %}
100
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
101
+ {{- '<|im_start|>user' }}
102
+ {%- endif %}
103
+ {{- '\n<tool_response>\n' }}
104
+ {{- message.content }}
105
+ {{- '\n</tool_response>' }}
106
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
107
+ {{- '<|im_end|>\n' }}
108
+ {%- elif loop.last %}
109
+ {{- '<|im_end|>\n' }}
110
+ {%- endif %}
111
+ {%- else %}
112
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
113
+ {%- endif %}
114
+ {%- endfor %}
115
+ {%- if add_generation_prompt %}
116
+ {{- '<|im_start|>assistant\n' }}
117
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,369 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3NextForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 151645,
11
+ "full_attention_interval": 4,
12
+ "head_dim": 256,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 2048,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 5120,
17
+ "layer_types": [
18
+ "linear_attention",
19
+ "linear_attention",
20
+ "linear_attention",
21
+ "full_attention",
22
+ "linear_attention",
23
+ "linear_attention",
24
+ "linear_attention",
25
+ "full_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "full_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "full_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "full_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "full_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "full_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "full_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "full_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "linear_attention",
57
+ "full_attention",
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "linear_attention",
61
+ "full_attention",
62
+ "linear_attention",
63
+ "linear_attention",
64
+ "linear_attention",
65
+ "full_attention"
66
+ ],
67
+ "linear_conv_kernel_dim": 4,
68
+ "linear_key_head_dim": 128,
69
+ "linear_num_key_heads": 16,
70
+ "linear_num_value_heads": 32,
71
+ "linear_value_head_dim": 128,
72
+ "max_position_embeddings": 262144,
73
+ "mlp_only_layers": [],
74
+ "model_type": "qwen3_next",
75
+ "moe_intermediate_size": 512,
76
+ "norm_topk_prob": true,
77
+ "num_attention_heads": 16,
78
+ "num_experts": 512,
79
+ "num_experts_per_tok": 10,
80
+ "num_hidden_layers": 48,
81
+ "num_key_value_heads": 2,
82
+ "output_router_logits": false,
83
+ "partial_rotary_factor": 0.25,
84
+ "rms_norm_eps": 1e-06,
85
+ "rope_scaling": null,
86
+ "rope_theta": 5000000,
87
+ "router_aux_loss_coef": 0.001,
88
+ "shared_expert_intermediate_size": 512,
89
+ "tie_word_embeddings": false,
90
+ "transformers_version": "4.57.6",
91
+ "use_cache": true,
92
+ "use_sliding_window": false,
93
+ "vocab_size": 151936,
94
+ "quantization_config": {
95
+ "config_groups": {
96
+ "group_0": {
97
+ "input_activations": {
98
+ "dynamic": false,
99
+ "num_bits": 4,
100
+ "type": "float",
101
+ "group_size": 16
102
+ },
103
+ "weights": {
104
+ "dynamic": false,
105
+ "num_bits": 4,
106
+ "type": "float",
107
+ "group_size": 16
108
+ },
109
+ "targets": [
110
+ "Linear"
111
+ ]
112
+ }
113
+ },
114
+ "ignore": [
115
+ "lm_head",
116
+ "model.layers.0.linear_attn.conv1d",
117
+ "model.layers.0.linear_attn.in_proj_ba",
118
+ "model.layers.0.linear_attn.in_proj_qkvz",
119
+ "model.layers.0.mlp.gate",
120
+ "model.layers.0.mlp.shared_expert_gate",
121
+ "model.layers.1.linear_attn.conv1d",
122
+ "model.layers.1.linear_attn.in_proj_ba",
123
+ "model.layers.1.linear_attn.in_proj_qkvz",
124
+ "model.layers.1.mlp.gate",
125
+ "model.layers.1.mlp.shared_expert_gate",
126
+ "model.layers.10.linear_attn.conv1d",
127
+ "model.layers.10.linear_attn.in_proj_ba",
128
+ "model.layers.10.linear_attn.in_proj_qkvz",
129
+ "model.layers.10.mlp.gate",
130
+ "model.layers.10.mlp.shared_expert_gate",
131
+ "model.layers.11.mlp.gate",
132
+ "model.layers.11.mlp.shared_expert_gate",
133
+ "model.layers.11.self_attn.k_proj",
134
+ "model.layers.11.self_attn.q_proj",
135
+ "model.layers.11.self_attn.v_proj",
136
+ "model.layers.12.linear_attn.conv1d",
137
+ "model.layers.12.linear_attn.in_proj_ba",
138
+ "model.layers.12.linear_attn.in_proj_qkvz",
139
+ "model.layers.12.mlp.gate",
140
+ "model.layers.12.mlp.shared_expert_gate",
141
+ "model.layers.13.linear_attn.conv1d",
142
+ "model.layers.13.linear_attn.in_proj_ba",
143
+ "model.layers.13.linear_attn.in_proj_qkvz",
144
+ "model.layers.13.mlp.gate",
145
+ "model.layers.13.mlp.shared_expert_gate",
146
+ "model.layers.14.linear_attn.conv1d",
147
+ "model.layers.14.linear_attn.in_proj_ba",
148
+ "model.layers.14.linear_attn.in_proj_qkvz",
149
+ "model.layers.14.mlp.gate",
150
+ "model.layers.14.mlp.shared_expert_gate",
151
+ "model.layers.15.mlp.gate",
152
+ "model.layers.15.mlp.shared_expert_gate",
153
+ "model.layers.15.self_attn.k_proj",
154
+ "model.layers.15.self_attn.q_proj",
155
+ "model.layers.15.self_attn.v_proj",
156
+ "model.layers.16.linear_attn.conv1d",
157
+ "model.layers.16.linear_attn.in_proj_ba",
158
+ "model.layers.16.linear_attn.in_proj_qkvz",
159
+ "model.layers.16.mlp.gate",
160
+ "model.layers.16.mlp.shared_expert_gate",
161
+ "model.layers.17.linear_attn.conv1d",
162
+ "model.layers.17.linear_attn.in_proj_ba",
163
+ "model.layers.17.linear_attn.in_proj_qkvz",
164
+ "model.layers.17.mlp.gate",
165
+ "model.layers.17.mlp.shared_expert_gate",
166
+ "model.layers.18.linear_attn.conv1d",
167
+ "model.layers.18.linear_attn.in_proj_ba",
168
+ "model.layers.18.linear_attn.in_proj_qkvz",
169
+ "model.layers.18.mlp.gate",
170
+ "model.layers.18.mlp.shared_expert_gate",
171
+ "model.layers.19.mlp.gate",
172
+ "model.layers.19.mlp.shared_expert_gate",
173
+ "model.layers.19.self_attn.k_proj",
174
+ "model.layers.19.self_attn.q_proj",
175
+ "model.layers.19.self_attn.v_proj",
176
+ "model.layers.2.linear_attn.conv1d",
177
+ "model.layers.2.linear_attn.in_proj_ba",
178
+ "model.layers.2.linear_attn.in_proj_qkvz",
179
+ "model.layers.2.mlp.gate",
180
+ "model.layers.2.mlp.shared_expert_gate",
181
+ "model.layers.20.linear_attn.conv1d",
182
+ "model.layers.20.linear_attn.in_proj_ba",
183
+ "model.layers.20.linear_attn.in_proj_qkvz",
184
+ "model.layers.20.mlp.gate",
185
+ "model.layers.20.mlp.shared_expert_gate",
186
+ "model.layers.21.linear_attn.conv1d",
187
+ "model.layers.21.linear_attn.in_proj_ba",
188
+ "model.layers.21.linear_attn.in_proj_qkvz",
189
+ "model.layers.21.mlp.gate",
190
+ "model.layers.21.mlp.shared_expert_gate",
191
+ "model.layers.22.linear_attn.conv1d",
192
+ "model.layers.22.linear_attn.in_proj_ba",
193
+ "model.layers.22.linear_attn.in_proj_qkvz",
194
+ "model.layers.22.mlp.gate",
195
+ "model.layers.22.mlp.shared_expert_gate",
196
+ "model.layers.23.mlp.gate",
197
+ "model.layers.23.mlp.shared_expert_gate",
198
+ "model.layers.23.self_attn.k_proj",
199
+ "model.layers.23.self_attn.q_proj",
200
+ "model.layers.23.self_attn.v_proj",
201
+ "model.layers.24.linear_attn.conv1d",
202
+ "model.layers.24.linear_attn.in_proj_ba",
203
+ "model.layers.24.linear_attn.in_proj_qkvz",
204
+ "model.layers.24.mlp.gate",
205
+ "model.layers.24.mlp.shared_expert_gate",
206
+ "model.layers.25.linear_attn.conv1d",
207
+ "model.layers.25.linear_attn.in_proj_ba",
208
+ "model.layers.25.linear_attn.in_proj_qkvz",
209
+ "model.layers.25.mlp.gate",
210
+ "model.layers.25.mlp.shared_expert_gate",
211
+ "model.layers.26.linear_attn.conv1d",
212
+ "model.layers.26.linear_attn.in_proj_ba",
213
+ "model.layers.26.linear_attn.in_proj_qkvz",
214
+ "model.layers.26.mlp.gate",
215
+ "model.layers.26.mlp.shared_expert_gate",
216
+ "model.layers.27.mlp.gate",
217
+ "model.layers.27.mlp.shared_expert_gate",
218
+ "model.layers.27.self_attn.k_proj",
219
+ "model.layers.27.self_attn.q_proj",
220
+ "model.layers.27.self_attn.v_proj",
221
+ "model.layers.28.linear_attn.conv1d",
222
+ "model.layers.28.linear_attn.in_proj_ba",
223
+ "model.layers.28.linear_attn.in_proj_qkvz",
224
+ "model.layers.28.mlp.gate",
225
+ "model.layers.28.mlp.shared_expert_gate",
226
+ "model.layers.29.linear_attn.conv1d",
227
+ "model.layers.29.linear_attn.in_proj_ba",
228
+ "model.layers.29.linear_attn.in_proj_qkvz",
229
+ "model.layers.29.mlp.gate",
230
+ "model.layers.29.mlp.shared_expert_gate",
231
+ "model.layers.3.mlp.gate",
232
+ "model.layers.3.mlp.shared_expert_gate",
233
+ "model.layers.3.self_attn.k_proj",
234
+ "model.layers.3.self_attn.q_proj",
235
+ "model.layers.3.self_attn.v_proj",
236
+ "model.layers.30.linear_attn.conv1d",
237
+ "model.layers.30.linear_attn.in_proj_ba",
238
+ "model.layers.30.linear_attn.in_proj_qkvz",
239
+ "model.layers.30.mlp.gate",
240
+ "model.layers.30.mlp.shared_expert_gate",
241
+ "model.layers.31.mlp.gate",
242
+ "model.layers.31.mlp.shared_expert_gate",
243
+ "model.layers.31.self_attn.k_proj",
244
+ "model.layers.31.self_attn.q_proj",
245
+ "model.layers.31.self_attn.v_proj",
246
+ "model.layers.32.linear_attn.conv1d",
247
+ "model.layers.32.linear_attn.in_proj_ba",
248
+ "model.layers.32.linear_attn.in_proj_qkvz",
249
+ "model.layers.32.mlp.gate",
250
+ "model.layers.32.mlp.shared_expert_gate",
251
+ "model.layers.33.linear_attn.conv1d",
252
+ "model.layers.33.linear_attn.in_proj_ba",
253
+ "model.layers.33.linear_attn.in_proj_qkvz",
254
+ "model.layers.33.mlp.gate",
255
+ "model.layers.33.mlp.shared_expert_gate",
256
+ "model.layers.34.linear_attn.conv1d",
257
+ "model.layers.34.linear_attn.in_proj_ba",
258
+ "model.layers.34.linear_attn.in_proj_qkvz",
259
+ "model.layers.34.mlp.gate",
260
+ "model.layers.34.mlp.shared_expert_gate",
261
+ "model.layers.35.mlp.gate",
262
+ "model.layers.35.mlp.shared_expert_gate",
263
+ "model.layers.35.self_attn.k_proj",
264
+ "model.layers.35.self_attn.q_proj",
265
+ "model.layers.35.self_attn.v_proj",
266
+ "model.layers.36.linear_attn.conv1d",
267
+ "model.layers.36.linear_attn.in_proj_ba",
268
+ "model.layers.36.linear_attn.in_proj_qkvz",
269
+ "model.layers.36.mlp.gate",
270
+ "model.layers.36.mlp.shared_expert_gate",
271
+ "model.layers.37.linear_attn.conv1d",
272
+ "model.layers.37.linear_attn.in_proj_ba",
273
+ "model.layers.37.linear_attn.in_proj_qkvz",
274
+ "model.layers.37.mlp.gate",
275
+ "model.layers.37.mlp.shared_expert_gate",
276
+ "model.layers.38.linear_attn.conv1d",
277
+ "model.layers.38.linear_attn.in_proj_ba",
278
+ "model.layers.38.linear_attn.in_proj_qkvz",
279
+ "model.layers.38.mlp.gate",
280
+ "model.layers.38.mlp.shared_expert_gate",
281
+ "model.layers.39.mlp.gate",
282
+ "model.layers.39.mlp.shared_expert_gate",
283
+ "model.layers.39.self_attn.k_proj",
284
+ "model.layers.39.self_attn.q_proj",
285
+ "model.layers.39.self_attn.v_proj",
286
+ "model.layers.4.linear_attn.conv1d",
287
+ "model.layers.4.linear_attn.in_proj_ba",
288
+ "model.layers.4.linear_attn.in_proj_qkvz",
289
+ "model.layers.4.mlp.gate",
290
+ "model.layers.4.mlp.shared_expert_gate",
291
+ "model.layers.40.linear_attn.conv1d",
292
+ "model.layers.40.linear_attn.in_proj_ba",
293
+ "model.layers.40.linear_attn.in_proj_qkvz",
294
+ "model.layers.40.mlp.gate",
295
+ "model.layers.40.mlp.shared_expert_gate",
296
+ "model.layers.41.linear_attn.conv1d",
297
+ "model.layers.41.linear_attn.in_proj_ba",
298
+ "model.layers.41.linear_attn.in_proj_qkvz",
299
+ "model.layers.41.mlp.gate",
300
+ "model.layers.41.mlp.shared_expert_gate",
301
+ "model.layers.42.linear_attn.conv1d",
302
+ "model.layers.42.linear_attn.in_proj_ba",
303
+ "model.layers.42.linear_attn.in_proj_qkvz",
304
+ "model.layers.42.mlp.gate",
305
+ "model.layers.42.mlp.shared_expert_gate",
306
+ "model.layers.43.mlp.gate",
307
+ "model.layers.43.mlp.shared_expert_gate",
308
+ "model.layers.43.self_attn.k_proj",
309
+ "model.layers.43.self_attn.q_proj",
310
+ "model.layers.43.self_attn.v_proj",
311
+ "model.layers.44.linear_attn.conv1d",
312
+ "model.layers.44.linear_attn.in_proj_ba",
313
+ "model.layers.44.linear_attn.in_proj_qkvz",
314
+ "model.layers.44.mlp.gate",
315
+ "model.layers.44.mlp.shared_expert_gate",
316
+ "model.layers.45.linear_attn.conv1d",
317
+ "model.layers.45.linear_attn.in_proj_ba",
318
+ "model.layers.45.linear_attn.in_proj_qkvz",
319
+ "model.layers.45.mlp.gate",
320
+ "model.layers.45.mlp.shared_expert_gate",
321
+ "model.layers.46.linear_attn.conv1d",
322
+ "model.layers.46.linear_attn.in_proj_ba",
323
+ "model.layers.46.linear_attn.in_proj_qkvz",
324
+ "model.layers.46.mlp.gate",
325
+ "model.layers.46.mlp.shared_expert_gate",
326
+ "model.layers.47.mlp.gate",
327
+ "model.layers.47.mlp.shared_expert_gate",
328
+ "model.layers.47.self_attn.k_proj",
329
+ "model.layers.47.self_attn.q_proj",
330
+ "model.layers.47.self_attn.v_proj",
331
+ "model.layers.5.linear_attn.conv1d",
332
+ "model.layers.5.linear_attn.in_proj_ba",
333
+ "model.layers.5.linear_attn.in_proj_qkvz",
334
+ "model.layers.5.mlp.gate",
335
+ "model.layers.5.mlp.shared_expert_gate",
336
+ "model.layers.6.linear_attn.conv1d",
337
+ "model.layers.6.linear_attn.in_proj_ba",
338
+ "model.layers.6.linear_attn.in_proj_qkvz",
339
+ "model.layers.6.mlp.gate",
340
+ "model.layers.6.mlp.shared_expert_gate",
341
+ "model.layers.7.mlp.gate",
342
+ "model.layers.7.mlp.shared_expert_gate",
343
+ "model.layers.7.self_attn.k_proj",
344
+ "model.layers.7.self_attn.q_proj",
345
+ "model.layers.7.self_attn.v_proj",
346
+ "model.layers.8.linear_attn.conv1d",
347
+ "model.layers.8.linear_attn.in_proj_ba",
348
+ "model.layers.8.linear_attn.in_proj_qkvz",
349
+ "model.layers.8.mlp.gate",
350
+ "model.layers.8.mlp.shared_expert_gate",
351
+ "model.layers.9.linear_attn.conv1d",
352
+ "model.layers.9.linear_attn.in_proj_ba",
353
+ "model.layers.9.linear_attn.in_proj_qkvz",
354
+ "model.layers.9.mlp.gate",
355
+ "model.layers.9.mlp.shared_expert_gate"
356
+ ],
357
+ "quant_algo": "NVFP4",
358
+ "kv_cache_scheme": {
359
+ "dynamic": false,
360
+ "num_bits": 8,
361
+ "type": "float"
362
+ },
363
+ "producer": {
364
+ "name": "modelopt",
365
+ "version": "0.42.0rc1.dev23+g5c4ef8e9a"
366
+ },
367
+ "quant_method": "modelopt"
368
+ }
369
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 1.0,
10
+ "top_k": 40,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.3"
13
+ }
hf_quant_config.json ADDED
@@ -0,0 +1,254 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "producer": {
3
+ "name": "modelopt",
4
+ "version": "0.42.0rc1.dev23+g5c4ef8e9a"
5
+ },
6
+ "quantization": {
7
+ "quant_algo": "NVFP4",
8
+ "kv_cache_quant_algo": "FP8",
9
+ "group_size": 16,
10
+ "exclude_modules": [
11
+ "lm_head",
12
+ "model.layers.0.linear_attn.conv1d",
13
+ "model.layers.0.linear_attn.in_proj_ba",
14
+ "model.layers.0.linear_attn.in_proj_qkvz",
15
+ "model.layers.0.mlp.gate",
16
+ "model.layers.0.mlp.shared_expert_gate",
17
+ "model.layers.1.linear_attn.conv1d",
18
+ "model.layers.1.linear_attn.in_proj_ba",
19
+ "model.layers.1.linear_attn.in_proj_qkvz",
20
+ "model.layers.1.mlp.gate",
21
+ "model.layers.1.mlp.shared_expert_gate",
22
+ "model.layers.10.linear_attn.conv1d",
23
+ "model.layers.10.linear_attn.in_proj_ba",
24
+ "model.layers.10.linear_attn.in_proj_qkvz",
25
+ "model.layers.10.mlp.gate",
26
+ "model.layers.10.mlp.shared_expert_gate",
27
+ "model.layers.11.mlp.gate",
28
+ "model.layers.11.mlp.shared_expert_gate",
29
+ "model.layers.11.self_attn.k_proj",
30
+ "model.layers.11.self_attn.q_proj",
31
+ "model.layers.11.self_attn.v_proj",
32
+ "model.layers.12.linear_attn.conv1d",
33
+ "model.layers.12.linear_attn.in_proj_ba",
34
+ "model.layers.12.linear_attn.in_proj_qkvz",
35
+ "model.layers.12.mlp.gate",
36
+ "model.layers.12.mlp.shared_expert_gate",
37
+ "model.layers.13.linear_attn.conv1d",
38
+ "model.layers.13.linear_attn.in_proj_ba",
39
+ "model.layers.13.linear_attn.in_proj_qkvz",
40
+ "model.layers.13.mlp.gate",
41
+ "model.layers.13.mlp.shared_expert_gate",
42
+ "model.layers.14.linear_attn.conv1d",
43
+ "model.layers.14.linear_attn.in_proj_ba",
44
+ "model.layers.14.linear_attn.in_proj_qkvz",
45
+ "model.layers.14.mlp.gate",
46
+ "model.layers.14.mlp.shared_expert_gate",
47
+ "model.layers.15.mlp.gate",
48
+ "model.layers.15.mlp.shared_expert_gate",
49
+ "model.layers.15.self_attn.k_proj",
50
+ "model.layers.15.self_attn.q_proj",
51
+ "model.layers.15.self_attn.v_proj",
52
+ "model.layers.16.linear_attn.conv1d",
53
+ "model.layers.16.linear_attn.in_proj_ba",
54
+ "model.layers.16.linear_attn.in_proj_qkvz",
55
+ "model.layers.16.mlp.gate",
56
+ "model.layers.16.mlp.shared_expert_gate",
57
+ "model.layers.17.linear_attn.conv1d",
58
+ "model.layers.17.linear_attn.in_proj_ba",
59
+ "model.layers.17.linear_attn.in_proj_qkvz",
60
+ "model.layers.17.mlp.gate",
61
+ "model.layers.17.mlp.shared_expert_gate",
62
+ "model.layers.18.linear_attn.conv1d",
63
+ "model.layers.18.linear_attn.in_proj_ba",
64
+ "model.layers.18.linear_attn.in_proj_qkvz",
65
+ "model.layers.18.mlp.gate",
66
+ "model.layers.18.mlp.shared_expert_gate",
67
+ "model.layers.19.mlp.gate",
68
+ "model.layers.19.mlp.shared_expert_gate",
69
+ "model.layers.19.self_attn.k_proj",
70
+ "model.layers.19.self_attn.q_proj",
71
+ "model.layers.19.self_attn.v_proj",
72
+ "model.layers.2.linear_attn.conv1d",
73
+ "model.layers.2.linear_attn.in_proj_ba",
74
+ "model.layers.2.linear_attn.in_proj_qkvz",
75
+ "model.layers.2.mlp.gate",
76
+ "model.layers.2.mlp.shared_expert_gate",
77
+ "model.layers.20.linear_attn.conv1d",
78
+ "model.layers.20.linear_attn.in_proj_ba",
79
+ "model.layers.20.linear_attn.in_proj_qkvz",
80
+ "model.layers.20.mlp.gate",
81
+ "model.layers.20.mlp.shared_expert_gate",
82
+ "model.layers.21.linear_attn.conv1d",
83
+ "model.layers.21.linear_attn.in_proj_ba",
84
+ "model.layers.21.linear_attn.in_proj_qkvz",
85
+ "model.layers.21.mlp.gate",
86
+ "model.layers.21.mlp.shared_expert_gate",
87
+ "model.layers.22.linear_attn.conv1d",
88
+ "model.layers.22.linear_attn.in_proj_ba",
89
+ "model.layers.22.linear_attn.in_proj_qkvz",
90
+ "model.layers.22.mlp.gate",
91
+ "model.layers.22.mlp.shared_expert_gate",
92
+ "model.layers.23.mlp.gate",
93
+ "model.layers.23.mlp.shared_expert_gate",
94
+ "model.layers.23.self_attn.k_proj",
95
+ "model.layers.23.self_attn.q_proj",
96
+ "model.layers.23.self_attn.v_proj",
97
+ "model.layers.24.linear_attn.conv1d",
98
+ "model.layers.24.linear_attn.in_proj_ba",
99
+ "model.layers.24.linear_attn.in_proj_qkvz",
100
+ "model.layers.24.mlp.gate",
101
+ "model.layers.24.mlp.shared_expert_gate",
102
+ "model.layers.25.linear_attn.conv1d",
103
+ "model.layers.25.linear_attn.in_proj_ba",
104
+ "model.layers.25.linear_attn.in_proj_qkvz",
105
+ "model.layers.25.mlp.gate",
106
+ "model.layers.25.mlp.shared_expert_gate",
107
+ "model.layers.26.linear_attn.conv1d",
108
+ "model.layers.26.linear_attn.in_proj_ba",
109
+ "model.layers.26.linear_attn.in_proj_qkvz",
110
+ "model.layers.26.mlp.gate",
111
+ "model.layers.26.mlp.shared_expert_gate",
112
+ "model.layers.27.mlp.gate",
113
+ "model.layers.27.mlp.shared_expert_gate",
114
+ "model.layers.27.self_attn.k_proj",
115
+ "model.layers.27.self_attn.q_proj",
116
+ "model.layers.27.self_attn.v_proj",
117
+ "model.layers.28.linear_attn.conv1d",
118
+ "model.layers.28.linear_attn.in_proj_ba",
119
+ "model.layers.28.linear_attn.in_proj_qkvz",
120
+ "model.layers.28.mlp.gate",
121
+ "model.layers.28.mlp.shared_expert_gate",
122
+ "model.layers.29.linear_attn.conv1d",
123
+ "model.layers.29.linear_attn.in_proj_ba",
124
+ "model.layers.29.linear_attn.in_proj_qkvz",
125
+ "model.layers.29.mlp.gate",
126
+ "model.layers.29.mlp.shared_expert_gate",
127
+ "model.layers.3.mlp.gate",
128
+ "model.layers.3.mlp.shared_expert_gate",
129
+ "model.layers.3.self_attn.k_proj",
130
+ "model.layers.3.self_attn.q_proj",
131
+ "model.layers.3.self_attn.v_proj",
132
+ "model.layers.30.linear_attn.conv1d",
133
+ "model.layers.30.linear_attn.in_proj_ba",
134
+ "model.layers.30.linear_attn.in_proj_qkvz",
135
+ "model.layers.30.mlp.gate",
136
+ "model.layers.30.mlp.shared_expert_gate",
137
+ "model.layers.31.mlp.gate",
138
+ "model.layers.31.mlp.shared_expert_gate",
139
+ "model.layers.31.self_attn.k_proj",
140
+ "model.layers.31.self_attn.q_proj",
141
+ "model.layers.31.self_attn.v_proj",
142
+ "model.layers.32.linear_attn.conv1d",
143
+ "model.layers.32.linear_attn.in_proj_ba",
144
+ "model.layers.32.linear_attn.in_proj_qkvz",
145
+ "model.layers.32.mlp.gate",
146
+ "model.layers.32.mlp.shared_expert_gate",
147
+ "model.layers.33.linear_attn.conv1d",
148
+ "model.layers.33.linear_attn.in_proj_ba",
149
+ "model.layers.33.linear_attn.in_proj_qkvz",
150
+ "model.layers.33.mlp.gate",
151
+ "model.layers.33.mlp.shared_expert_gate",
152
+ "model.layers.34.linear_attn.conv1d",
153
+ "model.layers.34.linear_attn.in_proj_ba",
154
+ "model.layers.34.linear_attn.in_proj_qkvz",
155
+ "model.layers.34.mlp.gate",
156
+ "model.layers.34.mlp.shared_expert_gate",
157
+ "model.layers.35.mlp.gate",
158
+ "model.layers.35.mlp.shared_expert_gate",
159
+ "model.layers.35.self_attn.k_proj",
160
+ "model.layers.35.self_attn.q_proj",
161
+ "model.layers.35.self_attn.v_proj",
162
+ "model.layers.36.linear_attn.conv1d",
163
+ "model.layers.36.linear_attn.in_proj_ba",
164
+ "model.layers.36.linear_attn.in_proj_qkvz",
165
+ "model.layers.36.mlp.gate",
166
+ "model.layers.36.mlp.shared_expert_gate",
167
+ "model.layers.37.linear_attn.conv1d",
168
+ "model.layers.37.linear_attn.in_proj_ba",
169
+ "model.layers.37.linear_attn.in_proj_qkvz",
170
+ "model.layers.37.mlp.gate",
171
+ "model.layers.37.mlp.shared_expert_gate",
172
+ "model.layers.38.linear_attn.conv1d",
173
+ "model.layers.38.linear_attn.in_proj_ba",
174
+ "model.layers.38.linear_attn.in_proj_qkvz",
175
+ "model.layers.38.mlp.gate",
176
+ "model.layers.38.mlp.shared_expert_gate",
177
+ "model.layers.39.mlp.gate",
178
+ "model.layers.39.mlp.shared_expert_gate",
179
+ "model.layers.39.self_attn.k_proj",
180
+ "model.layers.39.self_attn.q_proj",
181
+ "model.layers.39.self_attn.v_proj",
182
+ "model.layers.4.linear_attn.conv1d",
183
+ "model.layers.4.linear_attn.in_proj_ba",
184
+ "model.layers.4.linear_attn.in_proj_qkvz",
185
+ "model.layers.4.mlp.gate",
186
+ "model.layers.4.mlp.shared_expert_gate",
187
+ "model.layers.40.linear_attn.conv1d",
188
+ "model.layers.40.linear_attn.in_proj_ba",
189
+ "model.layers.40.linear_attn.in_proj_qkvz",
190
+ "model.layers.40.mlp.gate",
191
+ "model.layers.40.mlp.shared_expert_gate",
192
+ "model.layers.41.linear_attn.conv1d",
193
+ "model.layers.41.linear_attn.in_proj_ba",
194
+ "model.layers.41.linear_attn.in_proj_qkvz",
195
+ "model.layers.41.mlp.gate",
196
+ "model.layers.41.mlp.shared_expert_gate",
197
+ "model.layers.42.linear_attn.conv1d",
198
+ "model.layers.42.linear_attn.in_proj_ba",
199
+ "model.layers.42.linear_attn.in_proj_qkvz",
200
+ "model.layers.42.mlp.gate",
201
+ "model.layers.42.mlp.shared_expert_gate",
202
+ "model.layers.43.mlp.gate",
203
+ "model.layers.43.mlp.shared_expert_gate",
204
+ "model.layers.43.self_attn.k_proj",
205
+ "model.layers.43.self_attn.q_proj",
206
+ "model.layers.43.self_attn.v_proj",
207
+ "model.layers.44.linear_attn.conv1d",
208
+ "model.layers.44.linear_attn.in_proj_ba",
209
+ "model.layers.44.linear_attn.in_proj_qkvz",
210
+ "model.layers.44.mlp.gate",
211
+ "model.layers.44.mlp.shared_expert_gate",
212
+ "model.layers.45.linear_attn.conv1d",
213
+ "model.layers.45.linear_attn.in_proj_ba",
214
+ "model.layers.45.linear_attn.in_proj_qkvz",
215
+ "model.layers.45.mlp.gate",
216
+ "model.layers.45.mlp.shared_expert_gate",
217
+ "model.layers.46.linear_attn.conv1d",
218
+ "model.layers.46.linear_attn.in_proj_ba",
219
+ "model.layers.46.linear_attn.in_proj_qkvz",
220
+ "model.layers.46.mlp.gate",
221
+ "model.layers.46.mlp.shared_expert_gate",
222
+ "model.layers.47.mlp.gate",
223
+ "model.layers.47.mlp.shared_expert_gate",
224
+ "model.layers.47.self_attn.k_proj",
225
+ "model.layers.47.self_attn.q_proj",
226
+ "model.layers.47.self_attn.v_proj",
227
+ "model.layers.5.linear_attn.conv1d",
228
+ "model.layers.5.linear_attn.in_proj_ba",
229
+ "model.layers.5.linear_attn.in_proj_qkvz",
230
+ "model.layers.5.mlp.gate",
231
+ "model.layers.5.mlp.shared_expert_gate",
232
+ "model.layers.6.linear_attn.conv1d",
233
+ "model.layers.6.linear_attn.in_proj_ba",
234
+ "model.layers.6.linear_attn.in_proj_qkvz",
235
+ "model.layers.6.mlp.gate",
236
+ "model.layers.6.mlp.shared_expert_gate",
237
+ "model.layers.7.mlp.gate",
238
+ "model.layers.7.mlp.shared_expert_gate",
239
+ "model.layers.7.self_attn.k_proj",
240
+ "model.layers.7.self_attn.q_proj",
241
+ "model.layers.7.self_attn.v_proj",
242
+ "model.layers.8.linear_attn.conv1d",
243
+ "model.layers.8.linear_attn.in_proj_ba",
244
+ "model.layers.8.linear_attn.in_proj_qkvz",
245
+ "model.layers.8.mlp.gate",
246
+ "model.layers.8.mlp.shared_expert_gate",
247
+ "model.layers.9.linear_attn.conv1d",
248
+ "model.layers.9.linear_attn.in_proj_ba",
249
+ "model.layers.9.linear_attn.in_proj_qkvz",
250
+ "model.layers.9.mlp.gate",
251
+ "model.layers.9.mlp.shared_expert_gate"
252
+ ]
253
+ }
254
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ce0f3139d341c2bc8f75baa639a085a2fc65b7a0c7faf497eaa9c0ce10af20a
3
+ size 5003036968
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f19c0d1721da711cb8e85ea9ceb435fcfe76f40e53e1e7745671e276dd0c1e
3
+ size 5003483960
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dc5f135beef7f3b41153936da3cbd6d2fba74a57c7db4e9e810a6b6930f5f1a
3
+ size 5003514400
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dc1d9b71e55aaa9b8c6beb2aa4789f533d7e070b292943a6e5918fbc0f94abd
3
+ size 5003755712
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f43573a8d877dcd9b6ab6864aaaa2b843a27d68a1d84e9a191cfd994cbdc2274
3
+ size 5003581304
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0828942084085fcd6305b01fd97042f1e292cbd2c884ca77564a4911e63ceab1
3
+ size 5003516056
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37dac2aae0a30f65772dc46094f17a07d7da905bc470d3c2ca7de61fcf64ae2b
3
+ size 5003593008
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8018d978e3479037c12e9c63b99477784d58fb6a142cf6e888d0b35279e9020f
3
+ size 5003516072
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c0de497d2a40f7697f1bd8653e7bec8cc4722f603f8a8665854ddc578be3ff5
3
+ size 5003744824
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15debcb95636eacbd66e56806cf4828c5cc73777d056009cdd6a1da14d843c6
3
+ size 2424868248
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50f99846ba972853a3171baf1349e5b51be76effe30d5ec1e412e714439ea64e
3
+ size 28326603
special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|im_end|>"
25
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 1048576,
235
+ "pad_token": "<|im_end|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff