lmmy commited on
Commit
48db893
·
verified ·
1 Parent(s): 2f73106

Add files using upload-large-folder tool

Browse files
README.md ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: transformers
4
+ tags:
5
+ - language
6
+ - granite-4.0
7
+ - mlx
8
+ base_model: ibm-granite/granite-4.0-h-small
9
+ ---
10
+ ## 💫 Community Model> granite-4.0-h-small by ibm-granite
11
+
12
+ _👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)_.
13
+
14
+ **Model creator**: [ibm-granite](https://huggingface.co/ibm-granite)<br>
15
+ **Original model**: [granite-4.0-h-small](https://huggingface.co/ibm-granite/granite-4.0-h-small)<br>
16
+ **MLX quantization**: provided by [LM Studio team](https://x.com/lmstudio) using [mlx_lm](https://github.com/ml-explore/mlx-lm)<br>
17
+
18
+ ## Technical Details
19
+
20
+ 5-bit quantized version of granite-4.0-h-small using MLX, optimized for Apple Silicon.
21
+
22
+ ## Special thanks
23
+
24
+ 🙏 Special thanks to the [Apple Machine Learning Research](https://github.com/ml-explore) team for creating [MLX](https://github.com/ml-explore/mlx).
25
+
26
+ ## Disclaimers
27
+
28
+ LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.
chat_template.jinja ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>' %}
2
+ {%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool 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>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}
3
+ {%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within <documents></documents> XML tags:\n<documents>' %}
4
+ {%- set documents_system_message_suffix = '\n</documents>\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}
5
+ {%- if available_tools is defined and available_tools %}
6
+ {%- set tools = available_tools %}
7
+ {%- endif %}
8
+ {%- set ns = namespace(tools_system_message=tools_system_message_prefix,
9
+ documents_system_message=documents_system_message_prefix,
10
+ system_message=''
11
+ ) %}
12
+ {%- if tools %}
13
+ {%- for tool in tools %}
14
+ {%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %}
15
+ {%- endfor %}
16
+ {%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}
17
+ {%- else %}
18
+ {%- set ns.tools_system_message = '' %}
19
+ {%- endif %}
20
+ {%- if documents %}
21
+ {%- for document in documents %}
22
+ {%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %}
23
+ {%- endfor %}
24
+ {%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}
25
+ {%- else %}
26
+ {%- set ns.documents_system_message = '' %}
27
+ {%- endif %}
28
+ {%- if messages[0].role == 'system' %}
29
+ {%- if messages[0].content is string %}
30
+ {%- set ns.system_message = messages[0].content %}
31
+ {%- elif messages[0].content is iterable %}
32
+ {%- for entry in messages[0].content %}
33
+ {%- if entry.type== 'text' %}
34
+ {%- if ns.system_message != '' %}
35
+ {%- set ns.system_message = ns.system_message + '\n' %}
36
+ {%- endif %}
37
+ {%- set ns.system_message = ns.system_message + entry.text %}
38
+ {%- endif %}
39
+ {%- endfor %}
40
+ {%- endif %}
41
+ {%- if tools and documents %}
42
+ {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message + '\n\n' + ns.documents_system_message %}
43
+ {%- elif tools %}
44
+ {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %}
45
+ {%- elif documents %}
46
+ {%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %}
47
+ {%- endif %}
48
+ {%- else %}
49
+ {%- if tools and documents %}
50
+ {%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message %}
51
+ {%- elif tools %}
52
+ {%- set ns.system_message = ns.tools_system_message %}
53
+ {%- elif documents %}
54
+ {%- set ns.system_message = ns.documents_system_message %}
55
+ {%- endif %}
56
+ {%- endif %}
57
+ {%- if ns.system_message %}
58
+ {{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }}
59
+ {%- endif %}
60
+ {%- for message in messages %}
61
+ {%- set content = namespace(val='') %}
62
+ {%- if message.content is string %}
63
+ {%- set content.val = message.content %}
64
+ {%- else %}
65
+ {%- if message.content is iterable %}
66
+ {%- for entry in message.content %}
67
+ {%- if entry.type== 'text' %}
68
+ {%- if content.val != '' %}
69
+ {%- set content.val = content.val + '\n' %}
70
+ {%- endif %}
71
+ {%- set content.val = content.val + entry.text %}
72
+ {%- endif %}
73
+ {%- endfor %}
74
+ {%- endif %}
75
+ {%- endif %}
76
+ {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}
77
+ {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }}
78
+ {%- elif message.role == 'assistant' %}
79
+ {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}
80
+ {%- if message.tool_calls %}
81
+ {%- for tool_call in message.tool_calls %}
82
+ {%- if (loop.first and content.val) or (not loop.first) %}
83
+ {{- '\n' }}
84
+ {%- endif %}
85
+ {%- if tool_call.function %}
86
+ {%- set tool_call = tool_call.function %}
87
+ {%- endif %}
88
+ {{- '<tool_call>\n{"name": "' }}
89
+ {{- tool_call.name }}
90
+ {{- '", "arguments": ' }}
91
+ {%- if tool_call.arguments is string %}
92
+ {{- tool_call.arguments }}
93
+ {%- else %}
94
+ {{- tool_call.arguments | tojson }}
95
+ {%- endif %}
96
+ {{- '}\n</tool_call>' }}
97
+ {%- endfor %}
98
+ {%- endif %}
99
+ {{- '<|end_of_text|>\n' }}
100
+ {%- elif message.role == 'tool' %}
101
+ {%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}
102
+ {{- '<|start_of_role|>user<|end_of_role|>' }}
103
+ {%- endif %}
104
+ {{- '\n<tool_response>\n' }}
105
+ {{- content.val }}
106
+ {{- '\n</tool_response>' }}
107
+ {%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}
108
+ {{- '<|end_of_text|>\n' }}
109
+ {%- endif %}
110
+ {%- endif %}
111
+ {%- endfor %}
112
+ {%- if add_generation_prompt %}
113
+ {{- '<|start_of_role|>assistant<|end_of_role|>' }}
114
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,419 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GraniteMoeHybridForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attention_multiplier": 0.0078125,
8
+ "bos_token_id": 100257,
9
+ "embedding_multiplier": 12,
10
+ "eos_token_id": 100257,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.1,
14
+ "intermediate_size": 768,
15
+ "layer_types": [
16
+ "mamba",
17
+ "mamba",
18
+ "mamba",
19
+ "mamba",
20
+ "mamba",
21
+ "attention",
22
+ "mamba",
23
+ "mamba",
24
+ "mamba",
25
+ "mamba",
26
+ "mamba",
27
+ "mamba",
28
+ "mamba",
29
+ "mamba",
30
+ "mamba",
31
+ "attention",
32
+ "mamba",
33
+ "mamba",
34
+ "mamba",
35
+ "mamba",
36
+ "mamba",
37
+ "mamba",
38
+ "mamba",
39
+ "mamba",
40
+ "mamba",
41
+ "attention",
42
+ "mamba",
43
+ "mamba",
44
+ "mamba",
45
+ "mamba",
46
+ "mamba",
47
+ "mamba",
48
+ "mamba",
49
+ "mamba",
50
+ "mamba",
51
+ "attention",
52
+ "mamba",
53
+ "mamba",
54
+ "mamba",
55
+ "mamba"
56
+ ],
57
+ "logits_scaling": 16,
58
+ "mamba_chunk_size": 256,
59
+ "mamba_conv_bias": true,
60
+ "mamba_d_conv": 4,
61
+ "mamba_d_head": 64,
62
+ "mamba_d_state": 128,
63
+ "mamba_expand": 2,
64
+ "mamba_n_groups": 1,
65
+ "mamba_n_heads": 128,
66
+ "mamba_proj_bias": false,
67
+ "max_position_embeddings": 131072,
68
+ "model_type": "granitemoehybrid",
69
+ "normalization_function": "rmsnorm",
70
+ "num_attention_heads": 32,
71
+ "num_experts_per_tok": 10,
72
+ "num_hidden_layers": 40,
73
+ "num_key_value_heads": 8,
74
+ "num_local_experts": 72,
75
+ "output_router_logits": false,
76
+ "pad_token_id": 100256,
77
+ "position_embedding_type": "nope",
78
+ "quantization": {
79
+ "group_size": 64,
80
+ "bits": 5,
81
+ "mode": "affine",
82
+ "model.layers.0.block_sparse_moe.router.layer": {
83
+ "group_size": 64,
84
+ "bits": 8
85
+ },
86
+ "model.layers.1.block_sparse_moe.router.layer": {
87
+ "group_size": 64,
88
+ "bits": 8
89
+ },
90
+ "model.layers.2.block_sparse_moe.router.layer": {
91
+ "group_size": 64,
92
+ "bits": 8
93
+ },
94
+ "model.layers.3.block_sparse_moe.router.layer": {
95
+ "group_size": 64,
96
+ "bits": 8
97
+ },
98
+ "model.layers.4.block_sparse_moe.router.layer": {
99
+ "group_size": 64,
100
+ "bits": 8
101
+ },
102
+ "model.layers.5.block_sparse_moe.router.layer": {
103
+ "group_size": 64,
104
+ "bits": 8
105
+ },
106
+ "model.layers.6.block_sparse_moe.router.layer": {
107
+ "group_size": 64,
108
+ "bits": 8
109
+ },
110
+ "model.layers.7.block_sparse_moe.router.layer": {
111
+ "group_size": 64,
112
+ "bits": 8
113
+ },
114
+ "model.layers.8.block_sparse_moe.router.layer": {
115
+ "group_size": 64,
116
+ "bits": 8
117
+ },
118
+ "model.layers.9.block_sparse_moe.router.layer": {
119
+ "group_size": 64,
120
+ "bits": 8
121
+ },
122
+ "model.layers.10.block_sparse_moe.router.layer": {
123
+ "group_size": 64,
124
+ "bits": 8
125
+ },
126
+ "model.layers.11.block_sparse_moe.router.layer": {
127
+ "group_size": 64,
128
+ "bits": 8
129
+ },
130
+ "model.layers.12.block_sparse_moe.router.layer": {
131
+ "group_size": 64,
132
+ "bits": 8
133
+ },
134
+ "model.layers.13.block_sparse_moe.router.layer": {
135
+ "group_size": 64,
136
+ "bits": 8
137
+ },
138
+ "model.layers.14.block_sparse_moe.router.layer": {
139
+ "group_size": 64,
140
+ "bits": 8
141
+ },
142
+ "model.layers.15.block_sparse_moe.router.layer": {
143
+ "group_size": 64,
144
+ "bits": 8
145
+ },
146
+ "model.layers.16.block_sparse_moe.router.layer": {
147
+ "group_size": 64,
148
+ "bits": 8
149
+ },
150
+ "model.layers.17.block_sparse_moe.router.layer": {
151
+ "group_size": 64,
152
+ "bits": 8
153
+ },
154
+ "model.layers.18.block_sparse_moe.router.layer": {
155
+ "group_size": 64,
156
+ "bits": 8
157
+ },
158
+ "model.layers.19.block_sparse_moe.router.layer": {
159
+ "group_size": 64,
160
+ "bits": 8
161
+ },
162
+ "model.layers.20.block_sparse_moe.router.layer": {
163
+ "group_size": 64,
164
+ "bits": 8
165
+ },
166
+ "model.layers.21.block_sparse_moe.router.layer": {
167
+ "group_size": 64,
168
+ "bits": 8
169
+ },
170
+ "model.layers.22.block_sparse_moe.router.layer": {
171
+ "group_size": 64,
172
+ "bits": 8
173
+ },
174
+ "model.layers.23.block_sparse_moe.router.layer": {
175
+ "group_size": 64,
176
+ "bits": 8
177
+ },
178
+ "model.layers.24.block_sparse_moe.router.layer": {
179
+ "group_size": 64,
180
+ "bits": 8
181
+ },
182
+ "model.layers.25.block_sparse_moe.router.layer": {
183
+ "group_size": 64,
184
+ "bits": 8
185
+ },
186
+ "model.layers.26.block_sparse_moe.router.layer": {
187
+ "group_size": 64,
188
+ "bits": 8
189
+ },
190
+ "model.layers.27.block_sparse_moe.router.layer": {
191
+ "group_size": 64,
192
+ "bits": 8
193
+ },
194
+ "model.layers.28.block_sparse_moe.router.layer": {
195
+ "group_size": 64,
196
+ "bits": 8
197
+ },
198
+ "model.layers.29.block_sparse_moe.router.layer": {
199
+ "group_size": 64,
200
+ "bits": 8
201
+ },
202
+ "model.layers.30.block_sparse_moe.router.layer": {
203
+ "group_size": 64,
204
+ "bits": 8
205
+ },
206
+ "model.layers.31.block_sparse_moe.router.layer": {
207
+ "group_size": 64,
208
+ "bits": 8
209
+ },
210
+ "model.layers.32.block_sparse_moe.router.layer": {
211
+ "group_size": 64,
212
+ "bits": 8
213
+ },
214
+ "model.layers.33.block_sparse_moe.router.layer": {
215
+ "group_size": 64,
216
+ "bits": 8
217
+ },
218
+ "model.layers.34.block_sparse_moe.router.layer": {
219
+ "group_size": 64,
220
+ "bits": 8
221
+ },
222
+ "model.layers.35.block_sparse_moe.router.layer": {
223
+ "group_size": 64,
224
+ "bits": 8
225
+ },
226
+ "model.layers.36.block_sparse_moe.router.layer": {
227
+ "group_size": 64,
228
+ "bits": 8
229
+ },
230
+ "model.layers.37.block_sparse_moe.router.layer": {
231
+ "group_size": 64,
232
+ "bits": 8
233
+ },
234
+ "model.layers.38.block_sparse_moe.router.layer": {
235
+ "group_size": 64,
236
+ "bits": 8
237
+ },
238
+ "model.layers.39.block_sparse_moe.router.layer": {
239
+ "group_size": 64,
240
+ "bits": 8
241
+ }
242
+ },
243
+ "quantization_config": {
244
+ "group_size": 64,
245
+ "bits": 5,
246
+ "mode": "affine",
247
+ "model.layers.0.block_sparse_moe.router.layer": {
248
+ "group_size": 64,
249
+ "bits": 8
250
+ },
251
+ "model.layers.1.block_sparse_moe.router.layer": {
252
+ "group_size": 64,
253
+ "bits": 8
254
+ },
255
+ "model.layers.2.block_sparse_moe.router.layer": {
256
+ "group_size": 64,
257
+ "bits": 8
258
+ },
259
+ "model.layers.3.block_sparse_moe.router.layer": {
260
+ "group_size": 64,
261
+ "bits": 8
262
+ },
263
+ "model.layers.4.block_sparse_moe.router.layer": {
264
+ "group_size": 64,
265
+ "bits": 8
266
+ },
267
+ "model.layers.5.block_sparse_moe.router.layer": {
268
+ "group_size": 64,
269
+ "bits": 8
270
+ },
271
+ "model.layers.6.block_sparse_moe.router.layer": {
272
+ "group_size": 64,
273
+ "bits": 8
274
+ },
275
+ "model.layers.7.block_sparse_moe.router.layer": {
276
+ "group_size": 64,
277
+ "bits": 8
278
+ },
279
+ "model.layers.8.block_sparse_moe.router.layer": {
280
+ "group_size": 64,
281
+ "bits": 8
282
+ },
283
+ "model.layers.9.block_sparse_moe.router.layer": {
284
+ "group_size": 64,
285
+ "bits": 8
286
+ },
287
+ "model.layers.10.block_sparse_moe.router.layer": {
288
+ "group_size": 64,
289
+ "bits": 8
290
+ },
291
+ "model.layers.11.block_sparse_moe.router.layer": {
292
+ "group_size": 64,
293
+ "bits": 8
294
+ },
295
+ "model.layers.12.block_sparse_moe.router.layer": {
296
+ "group_size": 64,
297
+ "bits": 8
298
+ },
299
+ "model.layers.13.block_sparse_moe.router.layer": {
300
+ "group_size": 64,
301
+ "bits": 8
302
+ },
303
+ "model.layers.14.block_sparse_moe.router.layer": {
304
+ "group_size": 64,
305
+ "bits": 8
306
+ },
307
+ "model.layers.15.block_sparse_moe.router.layer": {
308
+ "group_size": 64,
309
+ "bits": 8
310
+ },
311
+ "model.layers.16.block_sparse_moe.router.layer": {
312
+ "group_size": 64,
313
+ "bits": 8
314
+ },
315
+ "model.layers.17.block_sparse_moe.router.layer": {
316
+ "group_size": 64,
317
+ "bits": 8
318
+ },
319
+ "model.layers.18.block_sparse_moe.router.layer": {
320
+ "group_size": 64,
321
+ "bits": 8
322
+ },
323
+ "model.layers.19.block_sparse_moe.router.layer": {
324
+ "group_size": 64,
325
+ "bits": 8
326
+ },
327
+ "model.layers.20.block_sparse_moe.router.layer": {
328
+ "group_size": 64,
329
+ "bits": 8
330
+ },
331
+ "model.layers.21.block_sparse_moe.router.layer": {
332
+ "group_size": 64,
333
+ "bits": 8
334
+ },
335
+ "model.layers.22.block_sparse_moe.router.layer": {
336
+ "group_size": 64,
337
+ "bits": 8
338
+ },
339
+ "model.layers.23.block_sparse_moe.router.layer": {
340
+ "group_size": 64,
341
+ "bits": 8
342
+ },
343
+ "model.layers.24.block_sparse_moe.router.layer": {
344
+ "group_size": 64,
345
+ "bits": 8
346
+ },
347
+ "model.layers.25.block_sparse_moe.router.layer": {
348
+ "group_size": 64,
349
+ "bits": 8
350
+ },
351
+ "model.layers.26.block_sparse_moe.router.layer": {
352
+ "group_size": 64,
353
+ "bits": 8
354
+ },
355
+ "model.layers.27.block_sparse_moe.router.layer": {
356
+ "group_size": 64,
357
+ "bits": 8
358
+ },
359
+ "model.layers.28.block_sparse_moe.router.layer": {
360
+ "group_size": 64,
361
+ "bits": 8
362
+ },
363
+ "model.layers.29.block_sparse_moe.router.layer": {
364
+ "group_size": 64,
365
+ "bits": 8
366
+ },
367
+ "model.layers.30.block_sparse_moe.router.layer": {
368
+ "group_size": 64,
369
+ "bits": 8
370
+ },
371
+ "model.layers.31.block_sparse_moe.router.layer": {
372
+ "group_size": 64,
373
+ "bits": 8
374
+ },
375
+ "model.layers.32.block_sparse_moe.router.layer": {
376
+ "group_size": 64,
377
+ "bits": 8
378
+ },
379
+ "model.layers.33.block_sparse_moe.router.layer": {
380
+ "group_size": 64,
381
+ "bits": 8
382
+ },
383
+ "model.layers.34.block_sparse_moe.router.layer": {
384
+ "group_size": 64,
385
+ "bits": 8
386
+ },
387
+ "model.layers.35.block_sparse_moe.router.layer": {
388
+ "group_size": 64,
389
+ "bits": 8
390
+ },
391
+ "model.layers.36.block_sparse_moe.router.layer": {
392
+ "group_size": 64,
393
+ "bits": 8
394
+ },
395
+ "model.layers.37.block_sparse_moe.router.layer": {
396
+ "group_size": 64,
397
+ "bits": 8
398
+ },
399
+ "model.layers.38.block_sparse_moe.router.layer": {
400
+ "group_size": 64,
401
+ "bits": 8
402
+ },
403
+ "model.layers.39.block_sparse_moe.router.layer": {
404
+ "group_size": 64,
405
+ "bits": 8
406
+ }
407
+ },
408
+ "residual_multiplier": 0.22,
409
+ "rms_norm_eps": 1e-05,
410
+ "rope_scaling": null,
411
+ "rope_theta": 10000,
412
+ "router_aux_loss_coef": 0.0,
413
+ "shared_intermediate_size": 1536,
414
+ "tie_word_embeddings": true,
415
+ "torch_dtype": "bfloat16",
416
+ "transformers_version": "4.56.0",
417
+ "use_cache": true,
418
+ "vocab_size": 100352
419
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 100257,
4
+ "eos_token_id": 100257,
5
+ "pad_token_id": 100256,
6
+ "transformers_version": "4.56.0"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b2c289b991661e4088543a3ee92c65d7fd91399f678702e0d0946f8184eb3fe
3
+ size 5281967892
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d427ef4e2dd3e13587065ea02b79443466c1141973da6cef1db5d4fbf9e4571a
3
+ size 5227429045
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c8e104168d185db2cecc0ae0e9ba830524520a6c202435adaaf7091f4073b8f
3
+ size 5311126621
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05176ca6d6d38ae0bd613c80994856ca390e851613a93ee1fd52cd4a4a150bd8
3
+ size 5311126567
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0299e6a8ec6494f068d6c91d65644547f2b6dbd1e1405664c9966fee2ac294d0
3
+ size 1018311476
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|end_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|unk|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,784 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "100256": {
6
+ "content": "<|pad|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "100257": {
14
+ "content": "<|end_of_text|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "100258": {
22
+ "content": "<|fim_prefix|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "100259": {
30
+ "content": "<|fim_middle|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "100260": {
38
+ "content": "<|fim_suffix|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "100261": {
46
+ "content": "<|fim_pad|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "100262": {
54
+ "content": "<|filename|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "100263": {
62
+ "content": "<|reponame|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "100264": {
70
+ "content": "<|start_of_role|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "100265": {
78
+ "content": "<|end_of_role|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "100266": {
86
+ "content": "<|unused_1|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "100267": {
94
+ "content": "<|start_of_plugin|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "100268": {
102
+ "content": "<|end_of_plugin|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "100269": {
110
+ "content": "<|unk|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "100270": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "100271": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "100272": {
134
+ "content": "<tool_response>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "100273": {
142
+ "content": "</tool_response>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "100274": {
150
+ "content": "<think>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "100275": {
158
+ "content": "</think>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "100276": {
166
+ "content": "<think_on>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "100277": {
174
+ "content": "<think_off>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "100278": {
182
+ "content": "<schema>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "100279": {
190
+ "content": "</schema>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "100280": {
198
+ "content": "<tools>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "100281": {
206
+ "content": "</tools>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "100282": {
214
+ "content": "<documents>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "100283": {
222
+ "content": "</documents>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "100284": {
230
+ "content": "<|unused_15|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "100285": {
238
+ "content": "<|unused_16|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "100286": {
246
+ "content": "<|unused_17|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "100287": {
254
+ "content": "<|unused_18|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "100288": {
262
+ "content": "<|unused_19|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "100289": {
270
+ "content": "<|unused_20|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "100290": {
278
+ "content": "<|unused_21|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "100291": {
286
+ "content": "<|unused_22|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "100292": {
294
+ "content": "<|unused_23|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "100293": {
302
+ "content": "<|unused_24|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "100294": {
310
+ "content": "<|unused_25|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "100295": {
318
+ "content": "<|unused_26|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "100296": {
326
+ "content": "<|unused_27|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "100297": {
334
+ "content": "<|unused_28|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "100298": {
342
+ "content": "<|unused_29|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "100299": {
350
+ "content": "<|unused_30|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "100300": {
358
+ "content": "<|unused_31|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "100301": {
366
+ "content": "<|unused_32|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "100302": {
374
+ "content": "<|unused_33|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "100303": {
382
+ "content": "<|unused_34|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "100304": {
390
+ "content": "<|unused_35|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "100305": {
398
+ "content": "<|unused_36|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "100306": {
406
+ "content": "<|unused_37|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "100307": {
414
+ "content": "<|unused_38|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "100308": {
422
+ "content": "<|unused_39|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "100309": {
430
+ "content": "<|unused_40|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "100310": {
438
+ "content": "<|unused_41|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "100311": {
446
+ "content": "<|unused_42|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "100312": {
454
+ "content": "<|unused_43|>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "100313": {
462
+ "content": "<|unused_44|>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "100314": {
470
+ "content": "<|unused_45|>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "100315": {
478
+ "content": "<|unused_46|>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "100316": {
486
+ "content": "<|unused_47|>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "100317": {
494
+ "content": "<|unused_48|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "100318": {
502
+ "content": "<|unused_49|>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "100319": {
510
+ "content": "<|unused_50|>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "100320": {
518
+ "content": "<|unused_51|>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "100321": {
526
+ "content": "<|unused_52|>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "100322": {
534
+ "content": "<|unused_53|>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "100323": {
542
+ "content": "<|unused_54|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "100324": {
550
+ "content": "<|unused_55|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "100325": {
558
+ "content": "<|unused_56|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "100326": {
566
+ "content": "<|unused_57|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "100327": {
574
+ "content": "<|unused_58|>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "100328": {
582
+ "content": "<|unused_59|>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "100329": {
590
+ "content": "<|unused_60|>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "100330": {
598
+ "content": "<|unused_61|>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "100331": {
606
+ "content": "<|unused_62|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "100332": {
614
+ "content": "<|unused_63|>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "100333": {
622
+ "content": "<|unused_64|>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "100334": {
630
+ "content": "<|unused_65|>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "100335": {
638
+ "content": "<|unused_66|>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "100336": {
646
+ "content": "<|unused_67|>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "100337": {
654
+ "content": "<|unused_68|>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "100338": {
662
+ "content": "<|unused_69|>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "100339": {
670
+ "content": "<|unused_70|>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "100340": {
678
+ "content": "<|unused_71|>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "100341": {
686
+ "content": "<|unused_72|>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "100342": {
694
+ "content": "<|unused_73|>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "100343": {
702
+ "content": "<|unused_74|>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "100344": {
710
+ "content": "<|unused_75|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "100345": {
718
+ "content": "<|unused_76|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "100346": {
726
+ "content": "<|unused_77|>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "100347": {
734
+ "content": "<|unused_78|>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "100348": {
742
+ "content": "<|unused_79|>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "100349": {
750
+ "content": "<|unused_80|>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "100350": {
758
+ "content": "<|unused_81|>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "100351": {
766
+ "content": "<|unused_82|>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ }
773
+ },
774
+ "bos_token": "<|end_of_text|>",
775
+ "clean_up_tokenization_spaces": false,
776
+ "eos_token": "<|end_of_text|>",
777
+ "extra_special_tokens": {},
778
+ "model_max_length": 1000000000000000019884624838656,
779
+ "pad_token": "<|pad|>",
780
+ "padding_side": "left",
781
+ "tokenizer_class": "GPT2Tokenizer",
782
+ "unk_token": "<|unk|>",
783
+ "chat_template": "{%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>' %}\n{%- set tools_system_message_suffix = '\\n</tools>\\n\\nFor each tool 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>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}\n{%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\\n\\nYou are given a list of documents within <documents></documents> XML tags:\\n<documents>' %}\n{%- set documents_system_message_suffix = '\\n</documents>\\n\\nWrite the response to the user\\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}\n{%- if available_tools is defined and available_tools %}\n {%- set tools = available_tools %}\n{%- endif %}\n{%- set ns = namespace(tools_system_message=tools_system_message_prefix,\n documents_system_message=documents_system_message_prefix,\n system_message=''\n ) %}\n{%- if tools %}\n {%- for tool in tools %}\n {%- set ns.tools_system_message = ns.tools_system_message + '\\n' + (tool | tojson) %}\n {%- endfor %}\n {%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}\n{%- else %}\n {%- set ns.tools_system_message = '' %}\n{%- endif %}\n{%- if documents %}\n {%- for document in documents %}\n {%- set ns.documents_system_message = ns.documents_system_message + '\\n' + (document | tojson) %}\n {%- endfor %}\n {%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}\n{%- else %}\n {%- set ns.documents_system_message = '' %}\n{%- endif %}\n{%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {%- set ns.system_message = messages[0].content %}\n {%- elif messages[0].content is iterable %}\n {%- for entry in messages[0].content %}\n {%- if entry.type== 'text' %}\n {%- if ns.system_message != '' %}\n {%- set ns.system_message = ns.system_message + '\\n' %}\n {%- endif %}\n {%- set ns.system_message = ns.system_message + entry.text %}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if tools and documents %}\n {%- set ns.system_message = ns.system_message + '\\n\\n' + ns.tools_system_message + '\\n\\n' + ns.documents_system_message %}\n {%- elif tools %}\n {%- set ns.system_message = ns.system_message + '\\n\\n' + ns.tools_system_message %}\n {%- elif documents %}\n {%- set ns.system_message = ns.system_message + '\\n\\n' + ns.documents_system_message %}\n {%- endif %}\n{%- else %}\n {%- if tools and documents %}\n {%- set ns.system_message = ns.tools_system_message + '\\n\\n' + ns.documents_system_message %}\n {%- elif tools %}\n {%- set ns.system_message = ns.tools_system_message %}\n {%- elif documents %}\n {%- set ns.system_message = ns.documents_system_message %}\n {%- endif %}\n{%- endif %}\n{%- if ns.system_message %}\n {{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\\n' }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = namespace(val='') %}\n {%- if message.content is string %}\n {%- set content.val = message.content %}\n {%- else %}\n {%- if message.content is iterable %}\n {%- for entry in message.content %}\n {%- if entry.type== 'text' %}\n {%- if content.val != '' %}\n {%- set content.val = content.val + '\\n' %}\n {%- endif %}\n {%- set content.val = content.val + entry.text %}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- endif %}\n {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}\n {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\\n' }}\n {%- elif message.role == 'assistant' %}\n {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content.val) 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 {{- '<|end_of_text|>\\n' }}\n {%- elif message.role == 'tool' %}\n {%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}\n {{- '<|start_of_role|>user<|end_of_role|>' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content.val }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}\n {{- '<|end_of_text|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_of_role|>assistant<|end_of_role|>' }}\n{%- endif %}"
784
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff