Upload 5 files
Browse files- config.json +3 -5
- generation_config.json +13 -0
- special_tokens_map.json +2 -2
- tokenizer.json +63 -63
- tokenizer_config.json +74 -65
config.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
-
"eos_token_id":
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
12 |
"initializer_range": 0.02,
|
@@ -17,7 +17,6 @@
|
|
17 |
"num_attention_heads": 32,
|
18 |
"num_hidden_layers": 32,
|
19 |
"num_key_value_heads": 8,
|
20 |
-
"pad_token_id": 128004,
|
21 |
"pretraining_tp": 1,
|
22 |
"rms_norm_eps": 1e-05,
|
23 |
"rope_scaling": {
|
@@ -30,8 +29,7 @@
|
|
30 |
"rope_theta": 500000.0,
|
31 |
"tie_word_embeddings": false,
|
32 |
"torch_dtype": "bfloat16",
|
33 |
-
"transformers_version": "4.44.0",
|
34 |
-
"unsloth_version": "2024.8",
|
35 |
"use_cache": true,
|
36 |
"vocab_size": 128256
|
37 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128009,
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
12 |
"initializer_range": 0.02,
|
|
|
17 |
"num_attention_heads": 32,
|
18 |
"num_hidden_layers": 32,
|
19 |
"num_key_value_heads": 8,
|
|
|
20 |
"pretraining_tp": 1,
|
21 |
"rms_norm_eps": 1e-05,
|
22 |
"rope_scaling": {
|
|
|
29 |
"rope_theta": 500000.0,
|
30 |
"tie_word_embeddings": false,
|
31 |
"torch_dtype": "bfloat16",
|
32 |
+
"transformers_version": "4.44.0.dev0",
|
|
|
33 |
"use_cache": true,
|
34 |
"vocab_size": 128256
|
35 |
}
|
generation_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 128000,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": [
|
6 |
+
128009,
|
7 |
+
128040,
|
8 |
+
128008
|
9 |
+
],
|
10 |
+
"temperature": 0.6,
|
11 |
+
"top_p": 0.9,
|
12 |
+
"transformers_version": "4.44.0.dev0"
|
13 |
+
}
|
special_tokens_map.json
CHANGED
@@ -7,14 +7,14 @@
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
-
"content": "<|
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
"pad_token": {
|
17 |
-
"content": "<|
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
"rstrip": false,
|
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "<|eot_id|>",
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
"pad_token": {
|
17 |
+
"content": "<|end_of_text|>",
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
"rstrip": false,
|
tokenizer.json
CHANGED
@@ -23,21 +23,21 @@
|
|
23 |
},
|
24 |
{
|
25 |
"id": 128002,
|
26 |
-
"content": "
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
-
"special":
|
32 |
},
|
33 |
{
|
34 |
"id": 128003,
|
35 |
-
"content": "
|
36 |
"single_word": false,
|
37 |
"lstrip": false,
|
38 |
"rstrip": false,
|
39 |
"normalized": false,
|
40 |
-
"special":
|
41 |
},
|
42 |
{
|
43 |
"id": 128004,
|
@@ -104,268 +104,268 @@
|
|
104 |
},
|
105 |
{
|
106 |
"id": 128011,
|
107 |
-
"content": "
|
108 |
"single_word": false,
|
109 |
"lstrip": false,
|
110 |
"rstrip": false,
|
111 |
"normalized": false,
|
112 |
-
"special":
|
113 |
},
|
114 |
{
|
115 |
"id": 128012,
|
116 |
-
"content": "
|
117 |
"single_word": false,
|
118 |
"lstrip": false,
|
119 |
"rstrip": false,
|
120 |
"normalized": false,
|
121 |
-
"special":
|
122 |
},
|
123 |
{
|
124 |
"id": 128013,
|
125 |
-
"content": "
|
126 |
"single_word": false,
|
127 |
"lstrip": false,
|
128 |
"rstrip": false,
|
129 |
"normalized": false,
|
130 |
-
"special":
|
131 |
},
|
132 |
{
|
133 |
"id": 128014,
|
134 |
-
"content": "
|
135 |
"single_word": false,
|
136 |
"lstrip": false,
|
137 |
"rstrip": false,
|
138 |
"normalized": false,
|
139 |
-
"special":
|
140 |
},
|
141 |
{
|
142 |
"id": 128015,
|
143 |
-
"content": "
|
144 |
"single_word": false,
|
145 |
"lstrip": false,
|
146 |
"rstrip": false,
|
147 |
"normalized": false,
|
148 |
-
"special":
|
149 |
},
|
150 |
{
|
151 |
"id": 128016,
|
152 |
-
"content": "
|
153 |
"single_word": false,
|
154 |
"lstrip": false,
|
155 |
"rstrip": false,
|
156 |
"normalized": false,
|
157 |
-
"special":
|
158 |
},
|
159 |
{
|
160 |
"id": 128017,
|
161 |
-
"content": "
|
162 |
"single_word": false,
|
163 |
"lstrip": false,
|
164 |
"rstrip": false,
|
165 |
"normalized": false,
|
166 |
-
"special":
|
167 |
},
|
168 |
{
|
169 |
"id": 128018,
|
170 |
-
"content": "
|
171 |
"single_word": false,
|
172 |
"lstrip": false,
|
173 |
"rstrip": false,
|
174 |
"normalized": false,
|
175 |
-
"special":
|
176 |
},
|
177 |
{
|
178 |
"id": 128019,
|
179 |
-
"content": "
|
180 |
"single_word": false,
|
181 |
"lstrip": false,
|
182 |
"rstrip": false,
|
183 |
"normalized": false,
|
184 |
-
"special":
|
185 |
},
|
186 |
{
|
187 |
"id": 128020,
|
188 |
-
"content": "
|
189 |
"single_word": false,
|
190 |
"lstrip": false,
|
191 |
"rstrip": false,
|
192 |
"normalized": false,
|
193 |
-
"special":
|
194 |
},
|
195 |
{
|
196 |
"id": 128021,
|
197 |
-
"content": "
|
198 |
"single_word": false,
|
199 |
"lstrip": false,
|
200 |
"rstrip": false,
|
201 |
"normalized": false,
|
202 |
-
"special":
|
203 |
},
|
204 |
{
|
205 |
"id": 128022,
|
206 |
-
"content": "
|
207 |
"single_word": false,
|
208 |
"lstrip": false,
|
209 |
"rstrip": false,
|
210 |
"normalized": false,
|
211 |
-
"special":
|
212 |
},
|
213 |
{
|
214 |
"id": 128023,
|
215 |
-
"content": "
|
216 |
"single_word": false,
|
217 |
"lstrip": false,
|
218 |
"rstrip": false,
|
219 |
"normalized": false,
|
220 |
-
"special":
|
221 |
},
|
222 |
{
|
223 |
"id": 128024,
|
224 |
-
"content": "
|
225 |
"single_word": false,
|
226 |
"lstrip": false,
|
227 |
"rstrip": false,
|
228 |
"normalized": false,
|
229 |
-
"special":
|
230 |
},
|
231 |
{
|
232 |
"id": 128025,
|
233 |
-
"content": "
|
234 |
"single_word": false,
|
235 |
"lstrip": false,
|
236 |
"rstrip": false,
|
237 |
"normalized": false,
|
238 |
-
"special":
|
239 |
},
|
240 |
{
|
241 |
"id": 128026,
|
242 |
-
"content": "
|
243 |
"single_word": false,
|
244 |
"lstrip": false,
|
245 |
"rstrip": false,
|
246 |
"normalized": false,
|
247 |
-
"special":
|
248 |
},
|
249 |
{
|
250 |
"id": 128027,
|
251 |
-
"content": "
|
252 |
"single_word": false,
|
253 |
"lstrip": false,
|
254 |
"rstrip": false,
|
255 |
"normalized": false,
|
256 |
-
"special":
|
257 |
},
|
258 |
{
|
259 |
"id": 128028,
|
260 |
-
"content": "
|
261 |
"single_word": false,
|
262 |
"lstrip": false,
|
263 |
"rstrip": false,
|
264 |
"normalized": false,
|
265 |
-
"special":
|
266 |
},
|
267 |
{
|
268 |
"id": 128029,
|
269 |
-
"content": "
|
270 |
"single_word": false,
|
271 |
"lstrip": false,
|
272 |
"rstrip": false,
|
273 |
"normalized": false,
|
274 |
-
"special":
|
275 |
},
|
276 |
{
|
277 |
"id": 128030,
|
278 |
-
"content": "
|
279 |
"single_word": false,
|
280 |
"lstrip": false,
|
281 |
"rstrip": false,
|
282 |
"normalized": false,
|
283 |
-
"special":
|
284 |
},
|
285 |
{
|
286 |
"id": 128031,
|
287 |
-
"content": "
|
288 |
"single_word": false,
|
289 |
"lstrip": false,
|
290 |
"rstrip": false,
|
291 |
"normalized": false,
|
292 |
-
"special":
|
293 |
},
|
294 |
{
|
295 |
"id": 128032,
|
296 |
-
"content": "
|
297 |
"single_word": false,
|
298 |
"lstrip": false,
|
299 |
"rstrip": false,
|
300 |
"normalized": false,
|
301 |
-
"special":
|
302 |
},
|
303 |
{
|
304 |
"id": 128033,
|
305 |
-
"content": "
|
306 |
"single_word": false,
|
307 |
"lstrip": false,
|
308 |
"rstrip": false,
|
309 |
"normalized": false,
|
310 |
-
"special":
|
311 |
},
|
312 |
{
|
313 |
"id": 128034,
|
314 |
-
"content": "
|
315 |
"single_word": false,
|
316 |
"lstrip": false,
|
317 |
"rstrip": false,
|
318 |
"normalized": false,
|
319 |
-
"special":
|
320 |
},
|
321 |
{
|
322 |
"id": 128035,
|
323 |
-
"content": "
|
324 |
"single_word": false,
|
325 |
"lstrip": false,
|
326 |
"rstrip": false,
|
327 |
"normalized": false,
|
328 |
-
"special":
|
329 |
},
|
330 |
{
|
331 |
"id": 128036,
|
332 |
-
"content": "
|
333 |
"single_word": false,
|
334 |
"lstrip": false,
|
335 |
"rstrip": false,
|
336 |
"normalized": false,
|
337 |
-
"special":
|
338 |
},
|
339 |
{
|
340 |
"id": 128037,
|
341 |
-
"content": "
|
342 |
"single_word": false,
|
343 |
"lstrip": false,
|
344 |
"rstrip": false,
|
345 |
"normalized": false,
|
346 |
-
"special":
|
347 |
},
|
348 |
{
|
349 |
"id": 128038,
|
350 |
-
"content": "
|
351 |
"single_word": false,
|
352 |
"lstrip": false,
|
353 |
"rstrip": false,
|
354 |
"normalized": false,
|
355 |
-
"special":
|
356 |
},
|
357 |
{
|
358 |
"id": 128039,
|
359 |
-
"content": "<|
|
360 |
"single_word": false,
|
361 |
"lstrip": false,
|
362 |
"rstrip": false,
|
363 |
"normalized": false,
|
364 |
-
"special":
|
365 |
},
|
366 |
{
|
367 |
"id": 128040,
|
368 |
-
"content": "<|
|
369 |
"single_word": false,
|
370 |
"lstrip": false,
|
371 |
"rstrip": false,
|
|
|
23 |
},
|
24 |
{
|
25 |
"id": 128002,
|
26 |
+
"content": "<tool_call>",
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
+
"special": false
|
32 |
},
|
33 |
{
|
34 |
"id": 128003,
|
35 |
+
"content": "<tool_response>",
|
36 |
"single_word": false,
|
37 |
"lstrip": false,
|
38 |
"rstrip": false,
|
39 |
"normalized": false,
|
40 |
+
"special": false
|
41 |
},
|
42 |
{
|
43 |
"id": 128004,
|
|
|
104 |
},
|
105 |
{
|
106 |
"id": 128011,
|
107 |
+
"content": "<tools>",
|
108 |
"single_word": false,
|
109 |
"lstrip": false,
|
110 |
"rstrip": false,
|
111 |
"normalized": false,
|
112 |
+
"special": false
|
113 |
},
|
114 |
{
|
115 |
"id": 128012,
|
116 |
+
"content": "</tools>",
|
117 |
"single_word": false,
|
118 |
"lstrip": false,
|
119 |
"rstrip": false,
|
120 |
"normalized": false,
|
121 |
+
"special": false
|
122 |
},
|
123 |
{
|
124 |
"id": 128013,
|
125 |
+
"content": "</tool_call>",
|
126 |
"single_word": false,
|
127 |
"lstrip": false,
|
128 |
"rstrip": false,
|
129 |
"normalized": false,
|
130 |
+
"special": false
|
131 |
},
|
132 |
{
|
133 |
"id": 128014,
|
134 |
+
"content": "</tool_response>",
|
135 |
"single_word": false,
|
136 |
"lstrip": false,
|
137 |
"rstrip": false,
|
138 |
"normalized": false,
|
139 |
+
"special": false
|
140 |
},
|
141 |
{
|
142 |
"id": 128015,
|
143 |
+
"content": "<schema>",
|
144 |
"single_word": false,
|
145 |
"lstrip": false,
|
146 |
"rstrip": false,
|
147 |
"normalized": false,
|
148 |
+
"special": false
|
149 |
},
|
150 |
{
|
151 |
"id": 128016,
|
152 |
+
"content": "</schema>",
|
153 |
"single_word": false,
|
154 |
"lstrip": false,
|
155 |
"rstrip": false,
|
156 |
"normalized": false,
|
157 |
+
"special": false
|
158 |
},
|
159 |
{
|
160 |
"id": 128017,
|
161 |
+
"content": "<scratch_pad>",
|
162 |
"single_word": false,
|
163 |
"lstrip": false,
|
164 |
"rstrip": false,
|
165 |
"normalized": false,
|
166 |
+
"special": false
|
167 |
},
|
168 |
{
|
169 |
"id": 128018,
|
170 |
+
"content": "</scratch_pad>",
|
171 |
"single_word": false,
|
172 |
"lstrip": false,
|
173 |
"rstrip": false,
|
174 |
"normalized": false,
|
175 |
+
"special": false
|
176 |
},
|
177 |
{
|
178 |
"id": 128019,
|
179 |
+
"content": "<SCRATCHPAD>",
|
180 |
"single_word": false,
|
181 |
"lstrip": false,
|
182 |
"rstrip": false,
|
183 |
"normalized": false,
|
184 |
+
"special": false
|
185 |
},
|
186 |
{
|
187 |
"id": 128020,
|
188 |
+
"content": "</SCRATCHPAD>",
|
189 |
"single_word": false,
|
190 |
"lstrip": false,
|
191 |
"rstrip": false,
|
192 |
"normalized": false,
|
193 |
+
"special": false
|
194 |
},
|
195 |
{
|
196 |
"id": 128021,
|
197 |
+
"content": "<REASONING>",
|
198 |
"single_word": false,
|
199 |
"lstrip": false,
|
200 |
"rstrip": false,
|
201 |
"normalized": false,
|
202 |
+
"special": false
|
203 |
},
|
204 |
{
|
205 |
"id": 128022,
|
206 |
+
"content": "</REASONING>",
|
207 |
"single_word": false,
|
208 |
"lstrip": false,
|
209 |
"rstrip": false,
|
210 |
"normalized": false,
|
211 |
+
"special": false
|
212 |
},
|
213 |
{
|
214 |
"id": 128023,
|
215 |
+
"content": "<INNER_MONOLOGUE>",
|
216 |
"single_word": false,
|
217 |
"lstrip": false,
|
218 |
"rstrip": false,
|
219 |
"normalized": false,
|
220 |
+
"special": false
|
221 |
},
|
222 |
{
|
223 |
"id": 128024,
|
224 |
+
"content": "</INNER_MONOLOGUE>",
|
225 |
"single_word": false,
|
226 |
"lstrip": false,
|
227 |
"rstrip": false,
|
228 |
"normalized": false,
|
229 |
+
"special": false
|
230 |
},
|
231 |
{
|
232 |
"id": 128025,
|
233 |
+
"content": "<PLAN>",
|
234 |
"single_word": false,
|
235 |
"lstrip": false,
|
236 |
"rstrip": false,
|
237 |
"normalized": false,
|
238 |
+
"special": false
|
239 |
},
|
240 |
{
|
241 |
"id": 128026,
|
242 |
+
"content": "</PLAN>",
|
243 |
"single_word": false,
|
244 |
"lstrip": false,
|
245 |
"rstrip": false,
|
246 |
"normalized": false,
|
247 |
+
"special": false
|
248 |
},
|
249 |
{
|
250 |
"id": 128027,
|
251 |
+
"content": "<EXECUTION>",
|
252 |
"single_word": false,
|
253 |
"lstrip": false,
|
254 |
"rstrip": false,
|
255 |
"normalized": false,
|
256 |
+
"special": false
|
257 |
},
|
258 |
{
|
259 |
"id": 128028,
|
260 |
+
"content": "</EXECUTION>",
|
261 |
"single_word": false,
|
262 |
"lstrip": false,
|
263 |
"rstrip": false,
|
264 |
"normalized": false,
|
265 |
+
"special": false
|
266 |
},
|
267 |
{
|
268 |
"id": 128029,
|
269 |
+
"content": "<REFLECTION>",
|
270 |
"single_word": false,
|
271 |
"lstrip": false,
|
272 |
"rstrip": false,
|
273 |
"normalized": false,
|
274 |
+
"special": false
|
275 |
},
|
276 |
{
|
277 |
"id": 128030,
|
278 |
+
"content": "</REFLECTION>",
|
279 |
"single_word": false,
|
280 |
"lstrip": false,
|
281 |
"rstrip": false,
|
282 |
"normalized": false,
|
283 |
+
"special": false
|
284 |
},
|
285 |
{
|
286 |
"id": 128031,
|
287 |
+
"content": "<THINKING>",
|
288 |
"single_word": false,
|
289 |
"lstrip": false,
|
290 |
"rstrip": false,
|
291 |
"normalized": false,
|
292 |
+
"special": false
|
293 |
},
|
294 |
{
|
295 |
"id": 128032,
|
296 |
+
"content": "</THINKING>",
|
297 |
"single_word": false,
|
298 |
"lstrip": false,
|
299 |
"rstrip": false,
|
300 |
"normalized": false,
|
301 |
+
"special": false
|
302 |
},
|
303 |
{
|
304 |
"id": 128033,
|
305 |
+
"content": "<SOLUTION>",
|
306 |
"single_word": false,
|
307 |
"lstrip": false,
|
308 |
"rstrip": false,
|
309 |
"normalized": false,
|
310 |
+
"special": false
|
311 |
},
|
312 |
{
|
313 |
"id": 128034,
|
314 |
+
"content": "</SOLUTION>",
|
315 |
"single_word": false,
|
316 |
"lstrip": false,
|
317 |
"rstrip": false,
|
318 |
"normalized": false,
|
319 |
+
"special": false
|
320 |
},
|
321 |
{
|
322 |
"id": 128035,
|
323 |
+
"content": "<EXPLANATION>",
|
324 |
"single_word": false,
|
325 |
"lstrip": false,
|
326 |
"rstrip": false,
|
327 |
"normalized": false,
|
328 |
+
"special": false
|
329 |
},
|
330 |
{
|
331 |
"id": 128036,
|
332 |
+
"content": "</EXPLANATION>",
|
333 |
"single_word": false,
|
334 |
"lstrip": false,
|
335 |
"rstrip": false,
|
336 |
"normalized": false,
|
337 |
+
"special": false
|
338 |
},
|
339 |
{
|
340 |
"id": 128037,
|
341 |
+
"content": "<UNIT_TEST>",
|
342 |
"single_word": false,
|
343 |
"lstrip": false,
|
344 |
"rstrip": false,
|
345 |
"normalized": false,
|
346 |
+
"special": false
|
347 |
},
|
348 |
{
|
349 |
"id": 128038,
|
350 |
+
"content": "</UNIT_TEST>",
|
351 |
"single_word": false,
|
352 |
"lstrip": false,
|
353 |
"rstrip": false,
|
354 |
"normalized": false,
|
355 |
+
"special": false
|
356 |
},
|
357 |
{
|
358 |
"id": 128039,
|
359 |
+
"content": "<|im_start|>",
|
360 |
"single_word": false,
|
361 |
"lstrip": false,
|
362 |
"rstrip": false,
|
363 |
"normalized": false,
|
364 |
+
"special": false
|
365 |
},
|
366 |
{
|
367 |
"id": 128040,
|
368 |
+
"content": "<|im_end|>",
|
369 |
"single_word": false,
|
370 |
"lstrip": false,
|
371 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
@@ -17,20 +17,20 @@
|
|
17 |
"special": true
|
18 |
},
|
19 |
"128002": {
|
20 |
-
"content": "
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
-
"special":
|
26 |
},
|
27 |
"128003": {
|
28 |
-
"content": "
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
-
"special":
|
34 |
},
|
35 |
"128004": {
|
36 |
"content": "<|finetune_right_pad_id|>",
|
@@ -89,239 +89,239 @@
|
|
89 |
"special": true
|
90 |
},
|
91 |
"128011": {
|
92 |
-
"content": "
|
93 |
"lstrip": false,
|
94 |
"normalized": false,
|
95 |
"rstrip": false,
|
96 |
"single_word": false,
|
97 |
-
"special":
|
98 |
},
|
99 |
"128012": {
|
100 |
-
"content": "
|
101 |
"lstrip": false,
|
102 |
"normalized": false,
|
103 |
"rstrip": false,
|
104 |
"single_word": false,
|
105 |
-
"special":
|
106 |
},
|
107 |
"128013": {
|
108 |
-
"content": "
|
109 |
"lstrip": false,
|
110 |
"normalized": false,
|
111 |
"rstrip": false,
|
112 |
"single_word": false,
|
113 |
-
"special":
|
114 |
},
|
115 |
"128014": {
|
116 |
-
"content": "
|
117 |
"lstrip": false,
|
118 |
"normalized": false,
|
119 |
"rstrip": false,
|
120 |
"single_word": false,
|
121 |
-
"special":
|
122 |
},
|
123 |
"128015": {
|
124 |
-
"content": "
|
125 |
"lstrip": false,
|
126 |
"normalized": false,
|
127 |
"rstrip": false,
|
128 |
"single_word": false,
|
129 |
-
"special":
|
130 |
},
|
131 |
"128016": {
|
132 |
-
"content": "
|
133 |
"lstrip": false,
|
134 |
"normalized": false,
|
135 |
"rstrip": false,
|
136 |
"single_word": false,
|
137 |
-
"special":
|
138 |
},
|
139 |
"128017": {
|
140 |
-
"content": "
|
141 |
"lstrip": false,
|
142 |
"normalized": false,
|
143 |
"rstrip": false,
|
144 |
"single_word": false,
|
145 |
-
"special":
|
146 |
},
|
147 |
"128018": {
|
148 |
-
"content": "
|
149 |
"lstrip": false,
|
150 |
"normalized": false,
|
151 |
"rstrip": false,
|
152 |
"single_word": false,
|
153 |
-
"special":
|
154 |
},
|
155 |
"128019": {
|
156 |
-
"content": "
|
157 |
"lstrip": false,
|
158 |
"normalized": false,
|
159 |
"rstrip": false,
|
160 |
"single_word": false,
|
161 |
-
"special":
|
162 |
},
|
163 |
"128020": {
|
164 |
-
"content": "
|
165 |
"lstrip": false,
|
166 |
"normalized": false,
|
167 |
"rstrip": false,
|
168 |
"single_word": false,
|
169 |
-
"special":
|
170 |
},
|
171 |
"128021": {
|
172 |
-
"content": "
|
173 |
"lstrip": false,
|
174 |
"normalized": false,
|
175 |
"rstrip": false,
|
176 |
"single_word": false,
|
177 |
-
"special":
|
178 |
},
|
179 |
"128022": {
|
180 |
-
"content": "
|
181 |
"lstrip": false,
|
182 |
"normalized": false,
|
183 |
"rstrip": false,
|
184 |
"single_word": false,
|
185 |
-
"special":
|
186 |
},
|
187 |
"128023": {
|
188 |
-
"content": "
|
189 |
"lstrip": false,
|
190 |
"normalized": false,
|
191 |
"rstrip": false,
|
192 |
"single_word": false,
|
193 |
-
"special":
|
194 |
},
|
195 |
"128024": {
|
196 |
-
"content": "
|
197 |
"lstrip": false,
|
198 |
"normalized": false,
|
199 |
"rstrip": false,
|
200 |
"single_word": false,
|
201 |
-
"special":
|
202 |
},
|
203 |
"128025": {
|
204 |
-
"content": "
|
205 |
"lstrip": false,
|
206 |
"normalized": false,
|
207 |
"rstrip": false,
|
208 |
"single_word": false,
|
209 |
-
"special":
|
210 |
},
|
211 |
"128026": {
|
212 |
-
"content": "
|
213 |
"lstrip": false,
|
214 |
"normalized": false,
|
215 |
"rstrip": false,
|
216 |
"single_word": false,
|
217 |
-
"special":
|
218 |
},
|
219 |
"128027": {
|
220 |
-
"content": "
|
221 |
"lstrip": false,
|
222 |
"normalized": false,
|
223 |
"rstrip": false,
|
224 |
"single_word": false,
|
225 |
-
"special":
|
226 |
},
|
227 |
"128028": {
|
228 |
-
"content": "
|
229 |
"lstrip": false,
|
230 |
"normalized": false,
|
231 |
"rstrip": false,
|
232 |
"single_word": false,
|
233 |
-
"special":
|
234 |
},
|
235 |
"128029": {
|
236 |
-
"content": "
|
237 |
"lstrip": false,
|
238 |
"normalized": false,
|
239 |
"rstrip": false,
|
240 |
"single_word": false,
|
241 |
-
"special":
|
242 |
},
|
243 |
"128030": {
|
244 |
-
"content": "
|
245 |
"lstrip": false,
|
246 |
"normalized": false,
|
247 |
"rstrip": false,
|
248 |
"single_word": false,
|
249 |
-
"special":
|
250 |
},
|
251 |
"128031": {
|
252 |
-
"content": "
|
253 |
"lstrip": false,
|
254 |
"normalized": false,
|
255 |
"rstrip": false,
|
256 |
"single_word": false,
|
257 |
-
"special":
|
258 |
},
|
259 |
"128032": {
|
260 |
-
"content": "
|
261 |
"lstrip": false,
|
262 |
"normalized": false,
|
263 |
"rstrip": false,
|
264 |
"single_word": false,
|
265 |
-
"special":
|
266 |
},
|
267 |
"128033": {
|
268 |
-
"content": "
|
269 |
"lstrip": false,
|
270 |
"normalized": false,
|
271 |
"rstrip": false,
|
272 |
"single_word": false,
|
273 |
-
"special":
|
274 |
},
|
275 |
"128034": {
|
276 |
-
"content": "
|
277 |
"lstrip": false,
|
278 |
"normalized": false,
|
279 |
"rstrip": false,
|
280 |
"single_word": false,
|
281 |
-
"special":
|
282 |
},
|
283 |
"128035": {
|
284 |
-
"content": "
|
285 |
"lstrip": false,
|
286 |
"normalized": false,
|
287 |
"rstrip": false,
|
288 |
"single_word": false,
|
289 |
-
"special":
|
290 |
},
|
291 |
"128036": {
|
292 |
-
"content": "
|
293 |
"lstrip": false,
|
294 |
"normalized": false,
|
295 |
"rstrip": false,
|
296 |
"single_word": false,
|
297 |
-
"special":
|
298 |
},
|
299 |
"128037": {
|
300 |
-
"content": "
|
301 |
"lstrip": false,
|
302 |
"normalized": false,
|
303 |
"rstrip": false,
|
304 |
"single_word": false,
|
305 |
-
"special":
|
306 |
},
|
307 |
"128038": {
|
308 |
-
"content": "
|
309 |
"lstrip": false,
|
310 |
"normalized": false,
|
311 |
"rstrip": false,
|
312 |
"single_word": false,
|
313 |
-
"special":
|
314 |
},
|
315 |
"128039": {
|
316 |
-
"content": "<|
|
317 |
"lstrip": false,
|
318 |
"normalized": false,
|
319 |
"rstrip": false,
|
320 |
"single_word": false,
|
321 |
-
"special":
|
322 |
},
|
323 |
"128040": {
|
324 |
-
"content": "<|
|
325 |
"lstrip": false,
|
326 |
"normalized": false,
|
327 |
"rstrip": false,
|
@@ -2050,14 +2050,23 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
-
"eos_token": "<|
|
2055 |
"model_input_names": [
|
2056 |
"input_ids",
|
2057 |
"attention_mask"
|
2058 |
],
|
2059 |
"model_max_length": 131072,
|
2060 |
"pad_token": "<|finetune_right_pad_id|>",
|
2061 |
-
"padding_side": "left",
|
2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
}
|
|
|
17 |
"special": true
|
18 |
},
|
19 |
"128002": {
|
20 |
+
"content": "<tool_call>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
+
"special": false
|
26 |
},
|
27 |
"128003": {
|
28 |
+
"content": "<tool_response>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
+
"special": false
|
34 |
},
|
35 |
"128004": {
|
36 |
"content": "<|finetune_right_pad_id|>",
|
|
|
89 |
"special": true
|
90 |
},
|
91 |
"128011": {
|
92 |
+
"content": "<tools>",
|
93 |
"lstrip": false,
|
94 |
"normalized": false,
|
95 |
"rstrip": false,
|
96 |
"single_word": false,
|
97 |
+
"special": false
|
98 |
},
|
99 |
"128012": {
|
100 |
+
"content": "</tools>",
|
101 |
"lstrip": false,
|
102 |
"normalized": false,
|
103 |
"rstrip": false,
|
104 |
"single_word": false,
|
105 |
+
"special": false
|
106 |
},
|
107 |
"128013": {
|
108 |
+
"content": "</tool_call>",
|
109 |
"lstrip": false,
|
110 |
"normalized": false,
|
111 |
"rstrip": false,
|
112 |
"single_word": false,
|
113 |
+
"special": false
|
114 |
},
|
115 |
"128014": {
|
116 |
+
"content": "</tool_response>",
|
117 |
"lstrip": false,
|
118 |
"normalized": false,
|
119 |
"rstrip": false,
|
120 |
"single_word": false,
|
121 |
+
"special": false
|
122 |
},
|
123 |
"128015": {
|
124 |
+
"content": "<schema>",
|
125 |
"lstrip": false,
|
126 |
"normalized": false,
|
127 |
"rstrip": false,
|
128 |
"single_word": false,
|
129 |
+
"special": false
|
130 |
},
|
131 |
"128016": {
|
132 |
+
"content": "</schema>",
|
133 |
"lstrip": false,
|
134 |
"normalized": false,
|
135 |
"rstrip": false,
|
136 |
"single_word": false,
|
137 |
+
"special": false
|
138 |
},
|
139 |
"128017": {
|
140 |
+
"content": "<scratch_pad>",
|
141 |
"lstrip": false,
|
142 |
"normalized": false,
|
143 |
"rstrip": false,
|
144 |
"single_word": false,
|
145 |
+
"special": false
|
146 |
},
|
147 |
"128018": {
|
148 |
+
"content": "</scratch_pad>",
|
149 |
"lstrip": false,
|
150 |
"normalized": false,
|
151 |
"rstrip": false,
|
152 |
"single_word": false,
|
153 |
+
"special": false
|
154 |
},
|
155 |
"128019": {
|
156 |
+
"content": "<SCRATCHPAD>",
|
157 |
"lstrip": false,
|
158 |
"normalized": false,
|
159 |
"rstrip": false,
|
160 |
"single_word": false,
|
161 |
+
"special": false
|
162 |
},
|
163 |
"128020": {
|
164 |
+
"content": "</SCRATCHPAD>",
|
165 |
"lstrip": false,
|
166 |
"normalized": false,
|
167 |
"rstrip": false,
|
168 |
"single_word": false,
|
169 |
+
"special": false
|
170 |
},
|
171 |
"128021": {
|
172 |
+
"content": "<REASONING>",
|
173 |
"lstrip": false,
|
174 |
"normalized": false,
|
175 |
"rstrip": false,
|
176 |
"single_word": false,
|
177 |
+
"special": false
|
178 |
},
|
179 |
"128022": {
|
180 |
+
"content": "</REASONING>",
|
181 |
"lstrip": false,
|
182 |
"normalized": false,
|
183 |
"rstrip": false,
|
184 |
"single_word": false,
|
185 |
+
"special": false
|
186 |
},
|
187 |
"128023": {
|
188 |
+
"content": "<INNER_MONOLOGUE>",
|
189 |
"lstrip": false,
|
190 |
"normalized": false,
|
191 |
"rstrip": false,
|
192 |
"single_word": false,
|
193 |
+
"special": false
|
194 |
},
|
195 |
"128024": {
|
196 |
+
"content": "</INNER_MONOLOGUE>",
|
197 |
"lstrip": false,
|
198 |
"normalized": false,
|
199 |
"rstrip": false,
|
200 |
"single_word": false,
|
201 |
+
"special": false
|
202 |
},
|
203 |
"128025": {
|
204 |
+
"content": "<PLAN>",
|
205 |
"lstrip": false,
|
206 |
"normalized": false,
|
207 |
"rstrip": false,
|
208 |
"single_word": false,
|
209 |
+
"special": false
|
210 |
},
|
211 |
"128026": {
|
212 |
+
"content": "</PLAN>",
|
213 |
"lstrip": false,
|
214 |
"normalized": false,
|
215 |
"rstrip": false,
|
216 |
"single_word": false,
|
217 |
+
"special": false
|
218 |
},
|
219 |
"128027": {
|
220 |
+
"content": "<EXECUTION>",
|
221 |
"lstrip": false,
|
222 |
"normalized": false,
|
223 |
"rstrip": false,
|
224 |
"single_word": false,
|
225 |
+
"special": false
|
226 |
},
|
227 |
"128028": {
|
228 |
+
"content": "</EXECUTION>",
|
229 |
"lstrip": false,
|
230 |
"normalized": false,
|
231 |
"rstrip": false,
|
232 |
"single_word": false,
|
233 |
+
"special": false
|
234 |
},
|
235 |
"128029": {
|
236 |
+
"content": "<REFLECTION>",
|
237 |
"lstrip": false,
|
238 |
"normalized": false,
|
239 |
"rstrip": false,
|
240 |
"single_word": false,
|
241 |
+
"special": false
|
242 |
},
|
243 |
"128030": {
|
244 |
+
"content": "</REFLECTION>",
|
245 |
"lstrip": false,
|
246 |
"normalized": false,
|
247 |
"rstrip": false,
|
248 |
"single_word": false,
|
249 |
+
"special": false
|
250 |
},
|
251 |
"128031": {
|
252 |
+
"content": "<THINKING>",
|
253 |
"lstrip": false,
|
254 |
"normalized": false,
|
255 |
"rstrip": false,
|
256 |
"single_word": false,
|
257 |
+
"special": false
|
258 |
},
|
259 |
"128032": {
|
260 |
+
"content": "</THINKING>",
|
261 |
"lstrip": false,
|
262 |
"normalized": false,
|
263 |
"rstrip": false,
|
264 |
"single_word": false,
|
265 |
+
"special": false
|
266 |
},
|
267 |
"128033": {
|
268 |
+
"content": "<SOLUTION>",
|
269 |
"lstrip": false,
|
270 |
"normalized": false,
|
271 |
"rstrip": false,
|
272 |
"single_word": false,
|
273 |
+
"special": false
|
274 |
},
|
275 |
"128034": {
|
276 |
+
"content": "</SOLUTION>",
|
277 |
"lstrip": false,
|
278 |
"normalized": false,
|
279 |
"rstrip": false,
|
280 |
"single_word": false,
|
281 |
+
"special": false
|
282 |
},
|
283 |
"128035": {
|
284 |
+
"content": "<EXPLANATION>",
|
285 |
"lstrip": false,
|
286 |
"normalized": false,
|
287 |
"rstrip": false,
|
288 |
"single_word": false,
|
289 |
+
"special": false
|
290 |
},
|
291 |
"128036": {
|
292 |
+
"content": "</EXPLANATION>",
|
293 |
"lstrip": false,
|
294 |
"normalized": false,
|
295 |
"rstrip": false,
|
296 |
"single_word": false,
|
297 |
+
"special": false
|
298 |
},
|
299 |
"128037": {
|
300 |
+
"content": "<UNIT_TEST>",
|
301 |
"lstrip": false,
|
302 |
"normalized": false,
|
303 |
"rstrip": false,
|
304 |
"single_word": false,
|
305 |
+
"special": false
|
306 |
},
|
307 |
"128038": {
|
308 |
+
"content": "</UNIT_TEST>",
|
309 |
"lstrip": false,
|
310 |
"normalized": false,
|
311 |
"rstrip": false,
|
312 |
"single_word": false,
|
313 |
+
"special": false
|
314 |
},
|
315 |
"128039": {
|
316 |
+
"content": "<|im_start|>",
|
317 |
"lstrip": false,
|
318 |
"normalized": false,
|
319 |
"rstrip": false,
|
320 |
"single_word": false,
|
321 |
+
"special": false
|
322 |
},
|
323 |
"128040": {
|
324 |
+
"content": "<|im_end|>",
|
325 |
"lstrip": false,
|
326 |
"normalized": false,
|
327 |
"rstrip": false,
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": [
|
2054 |
+
{
|
2055 |
+
"name": "default",
|
2056 |
+
"template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|eot_id|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|eot_id|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|
2057 |
+
},
|
2058 |
+
{
|
2059 |
+
"name": "tool_use",
|
2060 |
+
"template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n \"string\": \"str\",\n \"number\": \"float\",\n \"integer\": \"int\",\n \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n {{- \"list[\" + json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n {%- if json_spec.additionalProperties is defined %}\n {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n {%- else %}\n {{- \"dict\" }}\n {%- endif %}\n{%- elif json_spec.type is iterable %}\n {{- \"Union[\" }}\n {%- for t in json_spec.type %}\n {{- json_to_python_type({\"type\": t}) }}\n {%- if not loop.last %}\n {{- \",\" }} \n {%- endif %}\n {%- endfor %}\n {{- \"]\" }}\n{%- else %}\n {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- '{\"type\": \"function\", \"function\": ' }}\n {{- '{\"name\": \"' + tool.name + '\", ' }}\n {{- '\"description\": \"' + tool.name + '(' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- param_name + \": \" + json_to_python_type(param_fields) }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- if tool.return is defined %}\n {{- \" -> \" + json_to_python_type(tool.return) }}\n {%- endif %}\n {{- \" - \" + tool.description + \"\\n\\n\" }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {%- if loop.first %}\n {{- \" Args:\\n\" }}\n {%- endif %}\n {{- \" \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n {%- endfor %}\n {%- if tool.return is defined and tool.return.description is defined %}\n {{- \"\\n Returns:\\n \" + tool.return.description }}\n {%- endif %}\n {{- '\"' }}\n {{- ', \"parameters\": ' }}\n {%- if tool.parameters.properties | length == 0 %}\n {{- \"{}\" }}\n {%- else %}\n {{- tool.parameters|tojson }}\n {%- endif %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \"\\n\" }}\n {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"name\": <function-name>, \"arguments\": <args-dict>}\n' }}\n{{- '</tool_call><|im_end|>' }}\n{%- for message in messages %}\n {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- for tool_call in message.tool_calls %}\n {{- '\n<tool_call>\n' }} {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '{' }}\n {{- '\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\"}' }}\n {{- ', '}}\n {%- if tool_call.arguments is defined %}\n {{- '\"arguments\": ' }}\n {{- tool_call.arguments|tojson }}\n {%- endif %}\n {{- '\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if not message.name is defined %}\n {{- raise_exception(\"Tool response dicts require a 'name' key indicating the name of the called function!\") }}\n {%- endif %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>tool\\n' }}\n {%- endif %}\n {{- '<tool_response>\\n' }}\n {{- message.content }}\n {%- if not loop.last %}\n {{- '\\n</tool_response>\\n' }}\n {%- else %}\n {{- '\\n</tool_response>' }}\n {%- endif %}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>' }}\n {%- elif loop.last %}\n {{- '<|im_end|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
|
2061 |
+
}
|
2062 |
+
],
|
2063 |
"clean_up_tokenization_spaces": true,
|
2064 |
+
"eos_token": "<|eot_id|>",
|
2065 |
"model_input_names": [
|
2066 |
"input_ids",
|
2067 |
"attention_mask"
|
2068 |
],
|
2069 |
"model_max_length": 131072,
|
2070 |
"pad_token": "<|finetune_right_pad_id|>",
|
|
|
2071 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2072 |
}
|