littlebird13 commited on
Commit
d12b8b7
·
verified ·
1 Parent(s): 2ca648f

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3MoeForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 12288,
15
+ "max_position_embeddings": 40960,
16
+ "max_window_layers": 94,
17
+ "mlp_only_layers": [],
18
+ "model_type": "qwen3_moe",
19
+ "moe_intermediate_size": 1536,
20
+ "norm_topk_prob": true,
21
+ "num_attention_heads": 64,
22
+ "num_experts": 128,
23
+ "num_experts_per_tok": 8,
24
+ "num_hidden_layers": 94,
25
+ "num_key_value_heads": 4,
26
+ "output_router_logits": false,
27
+ "quantization": {
28
+ "group_size": 128,
29
+ "bits": 4
30
+ },
31
+ "quantization_config": {
32
+ "group_size": 128,
33
+ "bits": 4
34
+ },
35
+ "rms_norm_eps": 1e-06,
36
+ "rope_scaling": null,
37
+ "rope_theta": 1000000.0,
38
+ "router_aux_loss_coef": 0.001,
39
+ "sliding_window": null,
40
+ "tie_word_embeddings": false,
41
+ "torch_dtype": "float16",
42
+ "transformers_version": "4.51.3",
43
+ "use_cache": true,
44
+ "use_sliding_window": false,
45
+ "vocab_size": 151936
46
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f7562df94d8d0380c43f04d120dff6463bdae51c8318a92f8e9d0500d19302b
3
+ size 5189335695
model-00002-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ebad817bfde4866f0cd811089842e2280b123d32c0e1af96ef5664ad9563cb7
3
+ size 5286542082
model-00003-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9c643e4b890958202aeaee4b8ecd2148f9e884e9b18e5741ff53b72147aefd6
3
+ size 5286542053
model-00004-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e973bf4c36665e4d753a929a05ef68f303319a672633883cb5e4d1687a34ed20
3
+ size 5286542134
model-00005-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ce4553826ba14a09ee8702b192ec4c56f6e7fe1283586928ca097951a06f2e
3
+ size 5286542134
model-00006-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a8374e2547e1260f40088618a54f9706b14b885f7310ad018825a3e64d3e127
3
+ size 5286542132
model-00007-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc8390dad4ed7a19a4484659904d2fe03824beaba3a67bf0f6aa17a91aa13f5
3
+ size 5286542166
model-00008-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5100d916286eca5fbbf66e162adb85ce344f82d41cefe45184456d5b2ab0ea52
3
+ size 5286542186
model-00009-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08e6dce9a555e14c2ae57fb7c2a547014c5e226d530ea9fe93179640205d1501
3
+ size 5286542134
model-00010-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff151645211fa9575c4e061fac697db0eca75e61fd7c046a2919eb96735e4df0
3
+ size 5286542152
model-00011-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54a90ffd5bdd41a91a93f9f71aee57bcbfbf281864974f217d9153e4e8aba554
3
+ size 5286542190
model-00012-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e97e259b67d52d28660387e940a766e661fe863a194a2b5ccf394c96bf062dce
3
+ size 5286542182
model-00013-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3313c8d23774b267b3cff1ba3920a48d76d4402a3a4b4a28689eb0f44af0e8f
3
+ size 5286542138
model-00014-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58144f985c4e45d89f9c5f3df97f94135e82be17ee85eb30f18e29f10b12c817
3
+ size 5286542110
model-00015-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a32aabf4461a7de6433143e1f0dcf8298ddea7e789a7bb7312c59e5597924b72
3
+ size 5286542156
model-00016-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30238770ee52d2b5352518aa31ed05db54ddb460ba51d89dfde805ef1fce0a55
3
+ size 5286542194
model-00017-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d8165dd5dff9f86b8636c5c781d59674d3385aca93ad399442216ab8c5548b4
3
+ size 5286542184
model-00018-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05628b0f7dedd5ca75495621c0285576ad41c41ff7dc685e78d3a847b814dcda
3
+ size 5286542182
model-00019-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3353ad134d2f40a04c57b542a1c28037eb67c65bb924c6c3608238f3f63509f
3
+ size 5286542178
model-00020-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:670af478a66b81c685c933fe94449836c64e1142d26f8331874401f0e5400ad2
3
+ size 5286542128
model-00021-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c253013cc2b07d3f5b65251736e70852eacfce8eeb213df01f6d56b365d2a2
3
+ size 5286542124
model-00022-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13fef8f1185c128da7184ac93278de446814a94605f034ac99c1dc2510e5dd8e
3
+ size 5286542184
model-00023-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f17e6df6aaf8092524b14949040316309785c6fec16f027a7bd08c7a57e5c3e
3
+ size 5286542194
model-00024-of-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4fdec2a7aaebf527c82197e22e66fcab3a38482ab652790dfd7ff9eb356bca3
3
+ size 3401711759
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a34fae3b8cf36ce23636b7d35c2a99f10b2a1e246db58312b3b2c565c16bf3fd
3
+ size 11422836
tokenizer_config.json ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "128244": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151643": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151644": {
22
+ "content": "<|im_start|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151645": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151646": {
38
+ "content": "<|object_ref_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151647": {
46
+ "content": "<|object_ref_end|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151648": {
54
+ "content": "<|box_start|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151649": {
62
+ "content": "<|box_end|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151650": {
70
+ "content": "<|quad_start|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151651": {
78
+ "content": "<|quad_end|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151652": {
86
+ "content": "<|vision_start|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151653": {
94
+ "content": "<|vision_end|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151654": {
102
+ "content": "<|vision_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151655": {
110
+ "content": "<|image_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151656": {
118
+ "content": "<|video_pad|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "151657": {
126
+ "content": "<tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151658": {
134
+ "content": "</tool_call>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151659": {
142
+ "content": "<|fim_prefix|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151660": {
150
+ "content": "<|fim_middle|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151661": {
158
+ "content": "<|fim_suffix|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151662": {
166
+ "content": "<|fim_pad|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151663": {
174
+ "content": "<|repo_name|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151664": {
182
+ "content": "<|file_sep|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151665": {
190
+ "content": "<tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151666": {
198
+ "content": "</tool_response>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151667": {
206
+ "content": "<think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "151668": {
214
+ "content": "</think>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ }
221
+ },
222
+ "additional_special_tokens": [
223
+ "<|im_start|>",
224
+ "<|im_end|>",
225
+ "<|object_ref_start|>",
226
+ "<|object_ref_end|>",
227
+ "<|box_start|>",
228
+ "<|box_end|>",
229
+ "<|quad_start|>",
230
+ "<|quad_end|>",
231
+ "<|vision_start|>",
232
+ "<|vision_end|>",
233
+ "<|vision_pad|>",
234
+ "<|image_pad|>",
235
+ "<|video_pad|>"
236
+ ],
237
+ "bos_token": null,
238
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for index in range(ns.last_query_index, -1, -1) %}\n {%- set message = messages[index] %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not('<tool_response>' in message.content and '</tool_response>' in message.content) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
239
+ "clean_up_tokenization_spaces": false,
240
+ "eos_token": "<|im_end|>",
241
+ "errors": "replace",
242
+ "extra_special_tokens": {},
243
+ "model_max_length": 131072,
244
+ "pad_token": "<unk>",
245
+ "split_special_tokens": false,
246
+ "tokenizer_class": "Qwen2Tokenizer",
247
+ "unk_token": null
248
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff