webxos commited on
Commit
385fc44
·
verified ·
1 Parent(s): add2f9e

Upload 14 files

Browse files
Files changed (14) hide show
  1. LICENSE +15 -0
  2. config.json +46 -0
  3. gitattributes.txt +5 -0
  4. knowledge_graph.json +0 -0
  5. model.json +743 -0
  6. requirements.txt +4 -0
  7. run.sh +10 -0
  8. test.py +124 -0
  9. test.sh +45 -0
  10. test_readme.md +56 -0
  11. to_parquet.py +50 -0
  12. tokenizer_config.json +10 -0
  13. training_logs.json +122 -0
  14. vocab.json +29 -0
LICENSE ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ Licensed under the Apache License, Version 2.0 (the "License");
6
+ you may not use this file except in compliance with the License.
7
+ You may obtain a copy of the License at
8
+
9
+ http://www.apache.org/licenses/LICENSE-2.0
10
+
11
+ Unless required by applicable law or agreed to in writing, software
12
+ distributed under the License is distributed on an "AS IS" BASIS,
13
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ See the License for the specific language governing permissions and
15
+ limitations under the License.
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MicroDistilleryBigramForCausalLM"
4
+ ],
5
+ "model_type": "custom",
6
+ "custom_model_type": "micro-distillery-bigram",
7
+ "vocab_size": 256,
8
+ "max_position_embeddings": 1024,
9
+ "hidden_size": 512,
10
+ "num_hidden_layers": 0,
11
+ "num_attention_heads": 0,
12
+ "intermediate_size": 0,
13
+ "activation_function": "gelu_new",
14
+ "layer_norm_epsilon": 0.00001,
15
+ "use_cache": true,
16
+ "bos_token_id": 0,
17
+ "eos_token_id": 1,
18
+ "transformers_version": "4.44.0",
19
+ "library_name": "micro-distillery",
20
+ "micro_distillery": {
21
+ "format": "bigram-distilled",
22
+ "dialect": "character-level",
23
+ "reference_arch": "tiny-bigram",
24
+ "distill_from": [
25
+ "smollm2-135m",
26
+ "qwen2.5-0.5b",
27
+ "olmo2-1b",
28
+ "tinyllama-1.1b"
29
+ ],
30
+ "harmonic_seed": 1251963776,
31
+ "harmonic_frequencies": [
32
+ 1,
33
+ 1.618033988749895,
34
+ 2,
35
+ 3.141592653589793
36
+ ],
37
+ "grpo_config": {
38
+ "group_size": 8,
39
+ "kl_penalty": 0.1
40
+ },
41
+ "vae_config": {
42
+ "latent_dim": 32,
43
+ "filter_threshold": 0.7
44
+ }
45
+ }
46
+ }
gitattributes.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ *.json text eol=lf
2
+ *.py text eol=lf
3
+ *.sh text eol=lf
4
+ *.md text eol=lf
5
+ *.svg text eol=lf
knowledge_graph.json ADDED
The diff for this file is too large to render. See raw diff
 
model.json ADDED
@@ -0,0 +1,743 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "format": "micro-distill-bigram-v1",
3
+ "version": "3.1.2",
4
+ "arch": "tiny-bigram",
5
+ "created": "2026-10-23T16:28:35.871Z",
6
+ "bos_token": "<|endoftext|>",
7
+ "eos_token": "<|endoftext|>",
8
+ "vocab": [
9
+ "e",
10
+ "m",
11
+ "a",
12
+ "<|endoftext|>",
13
+ "o",
14
+ "l",
15
+ "i",
16
+ "v",
17
+ "s",
18
+ "b",
19
+ "p",
20
+ "h",
21
+ "c",
22
+ "r",
23
+ "t",
24
+ "y",
25
+ "n",
26
+ "g",
27
+ "z",
28
+ "f",
29
+ "d",
30
+ "u",
31
+ "k",
32
+ "w",
33
+ "q",
34
+ "x",
35
+ "j"
36
+ ],
37
+ "transitions": {
38
+ "<|endoftext|>": {
39
+ "e": 0.03142302367531452,
40
+ "o": 0.006241602882487984,
41
+ "a": 0.13683539045552387,
42
+ "i": 0.00951455566524227,
43
+ "s": 0.075713303821323,
44
+ "c": 0.044856353549692446,
45
+ "m": 0.09185606503030176,
46
+ "h": 0.017429946979891715,
47
+ "v": 0.00643578512973113,
48
+ "l": 0.03157079407182878,
49
+ "g": 0.013711930379224541,
50
+ "p": 0.010931761973188944,
51
+ "r": 0.050673835437968655,
52
+ "z": 0.021015923040907263,
53
+ "n": 0.022986913991083813,
54
+ "b": 0.029298521130275285,
55
+ "k": 0.20203639092131692,
56
+ "w": 0.005203461836372002,
57
+ "q": 0.0014049505137646039,
58
+ "j": 0.09180023734928434,
59
+ "d": 0.05014877415083315,
60
+ "x": 0.0020463409657006187,
61
+ "t": 0.029778397192620824,
62
+ "f": 0.006825951644421089,
63
+ "y": 0.009037178142104236,
64
+ "u": 0.0012226100695960135
65
+ },
66
+ "e": {
67
+ "m": 0.025967029323514614,
68
+ "l": 0.24598889424345088,
69
+ "<|endoftext|>": 0.11091007946776332,
70
+ "r": 0.11092201603804878,
71
+ "v": 0.013704562285453765,
72
+ "t": 0.01876368081204729,
73
+ "n": 0.24890167101258925,
74
+ "y": 0.04231356188792247,
75
+ "a": 0.024936430823551972,
76
+ "s": 0.02606023199063644,
77
+ "d": 0.011539144696850799,
78
+ "h": 0.004406472152052705,
79
+ "x": 0.003675654152584675,
80
+ "p": 0.0023203737029962217,
81
+ "e": 0.045733743306851295,
82
+ "i": 0.025306917815145966,
83
+ "c": 0.00461961392254015,
84
+ "b": 0.003521735339512525,
85
+ "o": 0.009130521419258793,
86
+ "g": 0.0034807330990385198,
87
+ "j": 0.0015869043742217268,
88
+ "k": 0.004956563933030847,
89
+ "w": 0.0013922932396154071,
90
+ "z": 0.00518049361004235,
91
+ "f": 0.0022833609129692674,
92
+ "u": 0.0020074743312177763,
93
+ "q": 0.00038984210709231397
94
+ },
95
+ "m": {
96
+ "m": 0.01686682274677333,
97
+ "a": 0.534391546567649,
98
+ "i": 0.16130853256142075,
99
+ "e": 0.10736346548079982,
100
+ "n": 0.0019443330297621907,
101
+ "o": 0.045316657502541983,
102
+ "b": 0.010888264966668264,
103
+ "y": 0.030250178386305896,
104
+ "c": 0.004958049225893587,
105
+ "<|endoftext|>": 0.05016379216786448,
106
+ "r": 0.009813778205091016,
107
+ "p": 0.003694232756548157,
108
+ "u": 0.013513114556847216,
109
+ "d": 0.0023331996357146274,
110
+ "s": 0.0034025828020838303,
111
+ "h": 0.00048608325744054767,
112
+ "l": 0.00048608325744054767,
113
+ "t": 0.0003888666059524383,
114
+ "z": 0.0010693831663692037,
115
+ "f": 0.00009721665148810958,
116
+ "j": 0.0006805165604167665,
117
+ "k": 0.00009721665148810958,
118
+ "w": 0.00019443330297621916,
119
+ "v": 0.00029164995446432843
120
+ },
121
+ "a": {
122
+ "<|endoftext|>": 0.009035430442451363,
123
+ "v": 0.0013837088443813086,
124
+ "b": 0.0008326306317732777,
125
+ "r": 0.008163787545456646,
126
+ "m": 0.0026290268087354155,
127
+ "i": 0.0031053602162910312,
128
+ "d": 0.0016510666281486983,
129
+ "c": 0.0007130248984741629,
130
+ "y": 0.003500000041606367,
131
+ "n": 0.9508573625941308,
132
+ "h": 0.004976385182189745,
133
+ "u": 0.0005924215237736252,
134
+ "t": 0.0010306233669295187,
135
+ "l": 0.005269895190012813,
136
+ "z": 0.0005919295545883038,
137
+ "o": 0.00008572772859554754,
138
+ "a": 0.0007691709800871202,
139
+ "e": 0.0009416442569542682,
140
+ "g": 0.0002511220285813439,
141
+ "s": 0.0016881654269621487,
142
+ "w": 0.00023327288195382475,
143
+ "k": 0.0008108490308702133,
144
+ "p": 0.0001115821229338873,
145
+ "x": 0.00027369252091573375,
146
+ "q": 0.0000816454558052833,
147
+ "j": 0.00023813257943207627,
148
+ "f": 0.00018234151796513268
149
+ },
150
+ "o": {
151
+ "l": 0.0531009817212646,
152
+ "p": 0.007725534064453676,
153
+ "t": 0.009595926522163506,
154
+ "f": 0.0027649279809623677,
155
+ "r": 0.10944278093037886,
156
+ "n": 0.5045604400195208,
157
+ "e": 0.010734426279030368,
158
+ "o": 0.010721408316010947,
159
+ "k": 0.005699062438061735,
160
+ "v": 0.01607729895419145,
161
+ "w": 0.009465176544800624,
162
+ "m": 0.02122488832444639,
163
+ "s": 0.04719774553170854,
164
+ "d": 0.017363044348284087,
165
+ "i": 0.00561117737312951,
166
+ "a": 0.012495149503918224,
167
+ "c": 0.009270640877344413,
168
+ "u": 0.028940888114147034,
169
+ "g": 0.0035781420930101194,
170
+ "y": 0.008779896069867165,
171
+ "h": 0.014575249886702139,
172
+ "x": 0.0036594635042149007,
173
+ "<|endoftext|>": 0.06952980658008302,
174
+ "b": 0.011751036700382439,
175
+ "z": 0.004544441810980966,
176
+ "j": 0.0013465012773276929,
177
+ "q": 0.00024396423361432656
178
+ },
179
+ "l": {
180
+ "i": 0.22810205695236277,
181
+ "l": 0.07203461496284747,
182
+ "a": 0.2292138156135785,
183
+ "o": 0.032167649887252646,
184
+ "y": 0.08232639171123646,
185
+ "<|endoftext|>": 0.05408875334285437,
186
+ "e": 0.2592742573297448,
187
+ "u": 0.01469670366985211,
188
+ "s": 0.003869362872319872,
189
+ "t": 0.0032842106218243274,
190
+ "d": 0.005922836233873203,
191
+ "b": 0.002140498610219503,
192
+ "v": 0.003074421453746258,
193
+ "m": 0.0024698060887148126,
194
+ "c": 0.001029085870297837,
195
+ "k": 0.0009879224354859251,
196
+ "n": 0.0005838173404188073,
197
+ "h": 0.0007821052614263568,
198
+ "g": 0.0002469806088714813,
199
+ "p": 0.0006174515221787031,
200
+ "r": 0.0007409418266144431,
201
+ "w": 0.0006586149569906163,
202
+ "z": 0.0004116343481191354,
203
+ "j": 0.0002469806088714813,
204
+ "f": 0.0009055955658620978,
205
+ "q": 0.00012349030443574064
206
+ },
207
+ "i": {
208
+ "v": 0.010726401577306817,
209
+ "a": 0.173537852053899,
210
+ "s": 0.06529206561284831,
211
+ "g": 0.017421307006281934,
212
+ "l": 0.08273866238259413,
213
+ "z": 0.010866485333275425,
214
+ "c": 0.02262738131431838,
215
+ "e": 0.17020436386660526,
216
+ "o": 0.026726601302798348,
217
+ "r": 0.034507975145164405,
218
+ "n": 0.14222037933034914,
219
+ "<|endoftext|>": 0.09764145124376364,
220
+ "y": 0.0310627019655093,
221
+ "t": 0.024587006223452692,
222
+ "p": 0.002079147013225985,
223
+ "m": 0.019668000159395245,
224
+ "d": 0.019632129797952334,
225
+ "f": 0.003962148081808006,
226
+ "x": 0.00407671773968004,
227
+ "k": 0.019130178060731473,
228
+ "b": 0.004366158529731695,
229
+ "u": 0.004451665859126867,
230
+ "q": 0.0021113499977034145,
231
+ "j": 0.0029814183585882073,
232
+ "h": 0.003849825040298841,
233
+ "i": 0.0032167934921609543,
234
+ "w": 0.0003138335114303369
235
+ },
236
+ "v": {
237
+ "i": 0.39715357592336453,
238
+ "a": 0.258909241675283,
239
+ "e": 0.19311760823045115,
240
+ "y": 0.03973397553744297,
241
+ "o": 0.052633965198211216,
242
+ "<|endoftext|>": 0.02889743675450403,
243
+ "k": 0.0009851398893580897,
244
+ "r": 0.015762238229729435,
245
+ "n": 0.0026270397049549064,
246
+ "v": 0.002298659741835542,
247
+ "l": 0.004597319483671084,
248
+ "u": 0.002298659741835542,
249
+ "b": 0.0003283799631193633,
250
+ "d": 0.0003283799631193633,
251
+ "h": 0.0003283799631193633
252
+ },
253
+ "s": {
254
+ "a": 0.19851094702547245,
255
+ "o": 0.06954257834226978,
256
+ "c": 0.006032827856426987,
257
+ "t": 0.10078228331669968,
258
+ "k": 0.008801946853878743,
259
+ "l": 0.031353378165552025,
260
+ "i": 0.07306074113887441,
261
+ "<|endoftext|>": 0.1175395960693857,
262
+ "e": 0.12181179557486599,
263
+ "h": 0.14722359463981322,
264
+ "m": 0.009049241784640484,
265
+ "y": 0.022734786239062374,
266
+ "s": 0.05266548018293353,
267
+ "u": 0.019273169657928375,
268
+ "p": 0.005127903677962943,
269
+ "r": 0.005530092201724737,
270
+ "w": 0.002413131142570796,
271
+ "n": 0.002413131142570796,
272
+ "d": 0.0009049241784640483,
273
+ "b": 0.0021114897497494464,
274
+ "v": 0.0014076598331662982,
275
+ "z": 0.0010054713094044977,
276
+ "j": 0.00020109426188089975,
277
+ "f": 0.00020109426188089975,
278
+ "q": 0.00010054713094044987,
279
+ "g": 0.00020109426188089975
280
+ },
281
+ "b": {
282
+ "e": 0.275648931135521,
283
+ "i": 0.07005557258612022,
284
+ "r": 0.3478982201567813,
285
+ "y": 0.02648277919203386,
286
+ "a": 0.11044389216453362,
287
+ "l": 0.032864171768427534,
288
+ "b": 0.01277318005795703,
289
+ "o": 0.033502311026066926,
290
+ "<|endoftext|>": 0.03637393768544406,
291
+ "u": 0.014358133296885815,
292
+ "h": 0.01375423099583411,
293
+ "t": 0.0006381392576393699,
294
+ "s": 0.0025525570305574797,
295
+ "c": 0.00031906962881968497,
296
+ "n": 0.0012762785152787399,
297
+ "d": 0.020739525873279503,
298
+ "j": 0.00031906962881968497
299
+ },
300
+ "p": {
301
+ "h": 0.18970279522817213,
302
+ "e": 0.18391998438707796,
303
+ "a": 0.2057098873763383,
304
+ "i": 0.056724855435875,
305
+ "r": 0.1662217626437635,
306
+ "o": 0.06163039844970236,
307
+ "p": 0.037139019228860266,
308
+ "y": 0.011158987954598363,
309
+ "t": 0.016188803253605773,
310
+ "b": 0.0018598313257663932,
311
+ "l": 0.014878650606131145,
312
+ "<|endoftext|>": 0.030687216875145466,
313
+ "s": 0.014878650606131145,
314
+ "u": 0.0037196626515327864,
315
+ "j": 0.0009299156628831966,
316
+ "f": 0.0009299156628831966,
317
+ "n": 0.0009299156628831966,
318
+ "c": 0.0009299156628831966,
319
+ "k": 0.0009299156628831966,
320
+ "m": 0.0009299156628831966
321
+ },
322
+ "h": {
323
+ "i": 0.07676388953380493,
324
+ "a": 0.4833643434721604,
325
+ "<|endoftext|>": 0.22037058834412154,
326
+ "l": 0.017826749841360793,
327
+ "e": 0.07097664704914336,
328
+ "o": 0.02934644140986343,
329
+ "n": 0.012623968946238589,
330
+ "r": 0.01866151931183097,
331
+ "t": 0.00649494054480391,
332
+ "y": 0.0205058788586088,
333
+ "u": 0.015185353949823233,
334
+ "m": 0.011436501795585315,
335
+ "z": 0.0018981692437279036,
336
+ "k": 0.0026528630394269488,
337
+ "v": 0.0035676433978500373,
338
+ "d": 0.002195472860215409,
339
+ "s": 0.0028358191111115677,
340
+ "w": 0.0009147803584230859,
341
+ "b": 0.0007318242867384691,
342
+ "j": 0.0008233023225807769,
343
+ "g": 0.00018295607168461727,
344
+ "p": 0.00009147803584230863,
345
+ "f": 0.00018295607168461727,
346
+ "c": 0.00018295607168461727,
347
+ "h": 0.00009147803584230863,
348
+ "q": 0.00009147803584230863
349
+ },
350
+ "c": {
351
+ "h": 0.2363610048725589,
352
+ "a": 0.21755720577835164,
353
+ "t": 0.008461181705858233,
354
+ "e": 0.15244833915902656,
355
+ "l": 0.030192075277345225,
356
+ "y": 0.02699757270344262,
357
+ "o": 0.10825203688844941,
358
+ "k": 0.0795362686799814,
359
+ "i": 0.0710526337185416,
360
+ "c": 0.010153418047029886,
361
+ "<|endoftext|>": 0.023449560727664263,
362
+ "q": 0.0026592285361268725,
363
+ "r": 0.019589392965669077,
364
+ "s": 0.0012087402436940342,
365
+ "j": 0.0007252441462164209,
366
+ "u": 0.008696868013916798,
367
+ "z": 0.000966992194955227,
368
+ "d": 0.00024174804873880676,
369
+ "p": 0.00024174804873880676,
370
+ "g": 0.0004834960974776135,
371
+ "x": 0.0007252441462164209
372
+ },
373
+ "r": {
374
+ "l": 0.02299894066198822,
375
+ "p": 0.0007048770813462356,
376
+ "<|endoftext|>": 0.06932969578669759,
377
+ "y": 0.05753578248751272,
378
+ "i": 0.35277700228839765,
379
+ "a": 0.16523452797066818,
380
+ "e": 0.1619626081086743,
381
+ "o": 0.0558169178971802,
382
+ "u": 0.013352017579696425,
383
+ "g": 0.0038264755844509934,
384
+ "s": 0.00956618896112748,
385
+ "k": 0.004531352665797229,
386
+ "d": 0.009797545973451005,
387
+ "m": 0.008769951147169375,
388
+ "n": 0.007048770813462359,
389
+ "r": 0.023955600928217694,
390
+ "t": 0.010472459494286929,
391
+ "c": 0.00498448793237695,
392
+ "h": 0.006092151917349601,
393
+ "b": 0.0020642828810854053,
394
+ "j": 0.0012587090738325633,
395
+ "w": 0.0010573156220193526,
396
+ "v": 0.004294570632593233,
397
+ "z": 0.001158012347925959,
398
+ "f": 0.00045313526657972294,
399
+ "q": 0.0008055738072528403,
400
+ "x": 0.00015104508885990743
401
+ },
402
+ "t": {
403
+ "t": 0.0600131484323132,
404
+ "e": 0.1589080466172033,
405
+ "h": 0.1308609345841191,
406
+ "<|endoftext|>": 0.07489279857348578,
407
+ "o": 0.12091768975465769,
408
+ "a": 0.1715452606891152,
409
+ "y": 0.057116400370843305,
410
+ "u": 0.01209448921062503,
411
+ "i": 0.10127372705823899,
412
+ "r": 0.056634636104415916,
413
+ "l": 0.021277470055567127,
414
+ "z": 0.016788837395424788,
415
+ "n": 0.0034112661876121906,
416
+ "s": 0.005427014389383029,
417
+ "c": 0.002635978417700326,
418
+ "g": 0.0003101151079647445,
419
+ "w": 0.0017056330938060953,
420
+ "x": 0.0003101151079647445,
421
+ "m": 0.000620230215929489,
422
+ "j": 0.0004651726619471169,
423
+ "v": 0.002325863309735584,
424
+ "f": 0.0003101151079647445,
425
+ "b": 0.00015505755398237224
426
+ },
427
+ "y": {
428
+ "n": 0.22316563388284957,
429
+ "<|endoftext|>": 0.1753931256745333,
430
+ "l": 0.12831483374304417,
431
+ "a": 0.22812315259109384,
432
+ "d": 0.02377026914971252,
433
+ "t": 0.009412774694817562,
434
+ "s": 0.03609888183940138,
435
+ "e": 0.030533935718727326,
436
+ "z": 0.006816474241461681,
437
+ "r": 0.026688046683839773,
438
+ "c": 0.010899950969858511,
439
+ "p": 0.0013108604310503227,
440
+ "v": 0.009263413712755617,
441
+ "j": 0.002009985994277163,
442
+ "o": 0.024407544057830563,
443
+ "u": 0.012322088051873044,
444
+ "k": 0.008350704462521624,
445
+ "m": 0.012933822919696523,
446
+ "b": 0.0023595487758905826,
447
+ "x": 0.0024469394712939374,
448
+ "g": 0.0027438228240021247,
449
+ "i": 0.016779013517444145,
450
+ "y": 0.002009985994277163,
451
+ "f": 0.001048688344840259,
452
+ "q": 0.0005243441724201295,
453
+ "h": 0.0019225952988738105,
454
+ "w": 0.0003495627816134197
455
+ },
456
+ "n": {
457
+ "<|endoftext|>": 0.17266047032911536,
458
+ "a": 0.4567259059114593,
459
+ "e": 0.055387155385966724,
460
+ "o": 0.018594521985652687,
461
+ "n": 0.11324060889563935,
462
+ "t": 0.012564920676996832,
463
+ "s": 0.0093061044675649,
464
+ "i": 0.09261754733022302,
465
+ "z": 0.004205470384620199,
466
+ "d": 0.0229558202111985,
467
+ "l": 0.004978381149516112,
468
+ "y": 0.012989849552394423,
469
+ "g": 0.007850716686758652,
470
+ "c": 0.00581311398273088,
471
+ "r": 0.0011233270286087644,
472
+ "k": 0.0016067238335517298,
473
+ "v": 0.0014041587857609556,
474
+ "h": 0.0006637841532688151,
475
+ "u": 0.002541378669250408,
476
+ "j": 0.001145008991725202,
477
+ "m": 0.0005199670936853475,
478
+ "w": 0.0002808317571521911,
479
+ "f": 0.00028809938259607407,
480
+ "b": 0.0002042412779288661,
481
+ "x": 0.00015318095844664965,
482
+ "q": 0.00005106031948221652,
483
+ "p": 0.00012765079870554144
484
+ },
485
+ "g": {
486
+ "a": 0.18149879545700293,
487
+ "r": 0.10293715094177608,
488
+ "e": 0.17769623854929115,
489
+ "i": 0.09608372462911129,
490
+ "h": 0.18952797477484265,
491
+ "g": 0.012137506684719912,
492
+ "n": 0.0131085072194975,
493
+ "o": 0.04251827100019904,
494
+ "t": 0.01505050828905268,
495
+ "w": 0.013315253355652616,
496
+ "l": 0.01616826049832008,
497
+ "u": 0.04126752272804772,
498
+ "y": 0.01505050828905268,
499
+ "d": 0.009358236672947811,
500
+ "<|endoftext|>": 0.05243402887799,
501
+ "s": 0.01456500802166389,
502
+ "b": 0.0014565008021663883,
503
+ "j": 0.0014565008021663883,
504
+ "m": 0.0029130016043327767,
505
+ "f": 0.0004855002673887963,
506
+ "z": 0.0004855002673887963,
507
+ "v": 0.0004855002673887963
508
+ },
509
+ "z": {
510
+ "a": 0.39907473306485103,
511
+ "o": 0.039742687470048874,
512
+ "e": 0.14998615048837555,
513
+ "i": 0.1575050154356656,
514
+ "u": 0.026374692593759724,
515
+ "l": 0.048031144523580836,
516
+ "m": 0.013039801662988688,
517
+ "h": 0.015535777829200927,
518
+ "r": 0.011561509082196034,
519
+ "<|endoftext|>": 0.057807545410980196,
520
+ "b": 0.0014942703394359726,
521
+ "y": 0.053110682346338034,
522
+ "z": 0.016258372146838167,
523
+ "n": 0.0014451886352745043,
524
+ "t": 0.0014451886352745043,
525
+ "k": 0.0007225943176372521,
526
+ "j": 0.0007225943176372521,
527
+ "s": 0.0014451886352745043,
528
+ "c": 0.0007225943176372521,
529
+ "v": 0.0007225943176372521,
530
+ "g": 0.00036129715881862606,
531
+ "p": 0.0007225943176372521,
532
+ "w": 0.0010838914764558806,
533
+ "d": 0.0007225943176372521,
534
+ "x": 0.00036129715881862606
535
+ },
536
+ "f": {
537
+ "i": 0.17346061112804378,
538
+ "a": 0.2812225926381684,
539
+ "r": 0.12359068542873126,
540
+ "e": 0.13334784480468378,
541
+ "f": 0.04770166806021204,
542
+ "l": 0.021682576391005473,
543
+ "s": 0.0065047729173016424,
544
+ "n": 0.00433651527820109,
545
+ "t": 0.019514318751904916,
546
+ "<|endoftext|>": 0.08673030556402189,
547
+ "u": 0.010841288195502737,
548
+ "y": 0.015177803473703826,
549
+ "o": 0.06504772917301643,
550
+ "k": 0.002168257639100545,
551
+ "z": 0.002168257639100545,
552
+ "w": 0.00433651527820109,
553
+ "h": 0.0010841288195502724,
554
+ "g": 0.0010841288195502724
555
+ },
556
+ "d": {
557
+ "i": 0.10003287325975194,
558
+ "d": 0.021466842505043316,
559
+ "r": 0.06817768437033934,
560
+ "y": 0.04761899172086091,
561
+ "e": 0.25203526107357926,
562
+ "l": 0.008644366109413399,
563
+ "a": 0.3060120780443587,
564
+ "n": 0.0046480141497892685,
565
+ "o": 0.06396591872915218,
566
+ "<|endoftext|>": 0.07434154854095536,
567
+ "g": 0.0036018192122555916,
568
+ "s": 0.004178110286216492,
569
+ "u": 0.013959842548469808,
570
+ "h": 0.01724705145276003,
571
+ "v": 0.002449237064333804,
572
+ "z": 0.0001440727684902236,
573
+ "j": 0.0012966549164120124,
574
+ "w": 0.003313673675275141,
575
+ "m": 0.004416722508209122,
576
+ "t": 0.0005762910739608944,
577
+ "f": 0.0007203638424511191,
578
+ "c": 0.0004322183054706708,
579
+ "k": 0.0004322183054706708,
580
+ "b": 0.0001440727684902236,
581
+ "q": 0.0001440727684902236
582
+ },
583
+ "u": {
584
+ "n": 0.09635480982334345,
585
+ "b": 0.032656144583595115,
586
+ "r": 0.1285347481858616,
587
+ "d": 0.04126923265328236,
588
+ "c": 0.03240927570399761,
589
+ "t": 0.025718426298279095,
590
+ "m": 0.04673133697504026,
591
+ "i": 0.03873106764582303,
592
+ "l": 0.09671461337281026,
593
+ "e": 0.056163026960657975,
594
+ "s": 0.15710845852713717,
595
+ "a": 0.05149461573347472,
596
+ "p": 0.005034450594795742,
597
+ "g": 0.014262161284590218,
598
+ "z": 0.01406698240896419,
599
+ "x": 0.01069610615600794,
600
+ "v": 0.011227658883613574,
601
+ "<|endoftext|>": 0.04703478721513798,
602
+ "o": 0.0030345024009766435,
603
+ "h": 0.018536437449367043,
604
+ "w": 0.026096720648399123,
605
+ "j": 0.004248303361367295,
606
+ "k": 0.02822087232908278,
607
+ "q": 0.0030345024009766435,
608
+ "y": 0.0039448531212696375,
609
+ "f": 0.0057655545618556245,
610
+ "u": 0.0009103507202929931
611
+ },
612
+ "k": {
613
+ "l": 0.020104459098631424,
614
+ "y": 0.05296466284425289,
615
+ "e": 0.15764467906657353,
616
+ "i": 0.08211926608512035,
617
+ "a": 0.5054520873000489,
618
+ "h": 0.03982737457538952,
619
+ "o": 0.04858008504725666,
620
+ "r": 0.013629555602111234,
621
+ "s": 0.013098918219566569,
622
+ "<|endoftext|>": 0.04539017140886589,
623
+ "t": 0.0021257105067512957,
624
+ "k": 0.0025575133694805347,
625
+ "u": 0.006252089725739097,
626
+ "n": 0.0032510866573843343,
627
+ "w": 0.004251421013502591,
628
+ "m": 0.0011253761506330388,
629
+ "c": 0.00025008358902956407,
630
+ "j": 0.00025008358902956407,
631
+ "z": 0.00025008358902956407,
632
+ "f": 0.00012504179451478203,
633
+ "b": 0.00025008358902956407,
634
+ "d": 0.00025008358902956407,
635
+ "v": 0.00025008358902956407
636
+ },
637
+ "w": {
638
+ "i": 0.16574776323603124,
639
+ "<|endoftext|>": 0.05314454338034744,
640
+ "a": 0.2978965654830795,
641
+ "y": 0.07606964052481127,
642
+ "e": 0.16559280174046614,
643
+ "r": 0.02292509714446362,
644
+ "h": 0.023967147014666495,
645
+ "s": 0.021487840407348798,
646
+ "n": 0.06375336469748158,
647
+ "u": 0.026051246755072296,
648
+ "o": 0.037513795327304096,
649
+ "t": 0.008336398961623128,
650
+ "l": 0.013546648312637586,
651
+ "d": 0.008336398961623128,
652
+ "b": 0.001042049870202891,
653
+ "w": 0.002084099740405782,
654
+ "m": 0.002084099740405782,
655
+ "f": 0.002084099740405782,
656
+ "k": 0.0062522992212173485,
657
+ "z": 0.001042049870202891,
658
+ "g": 0.001042049870202891
659
+ },
660
+ "q": {
661
+ "u": 0.7560875414921902,
662
+ "r": 0.003670327871321313,
663
+ "<|endoftext|>": 0.10276918039699677,
664
+ "s": 0.007340655742642626,
665
+ "a": 0.04938508132778029,
666
+ "i": 0.04771426232717707,
667
+ "l": 0.003670327871321313,
668
+ "w": 0.011010983613963935,
669
+ "e": 0.003670327871321313,
670
+ "m": 0.007340655742642626,
671
+ "o": 0.007340655742642626
672
+ },
673
+ "x": {
674
+ "a": 0.15080347636246527,
675
+ "i": 0.14405057565273852,
676
+ "<|endoftext|>": 0.23161072948087372,
677
+ "l": 0.05926946822294173,
678
+ "e": 0.055166704001403076,
679
+ "o": 0.05969981060917997,
680
+ "y": 0.042367816368452556,
681
+ "t": 0.09885823819305581,
682
+ "w": 0.004236781636845251,
683
+ "u": 0.007061302728075419,
684
+ "c": 0.0056490421824603385,
685
+ "x": 0.0536659007333732,
686
+ "z": 0.0268329503666866,
687
+ "s": 0.04378007691406764,
688
+ "n": 0.0014122605456150846,
689
+ "f": 0.004236781636845251,
690
+ "h": 0.0014122605456150846,
691
+ "d": 0.007061302728075419,
692
+ "b": 0.0014122605456150846,
693
+ "m": 0.0014122605456150846
694
+ },
695
+ "j": {
696
+ "o": 0.15859926899904409,
697
+ "u": 0.06058380320499384,
698
+ "a": 0.564341549081726,
699
+ "e": 0.13621573780724716,
700
+ "i": 0.031853632391741535,
701
+ "h": 0.011648504722920366,
702
+ "r": 0.002847412265602756,
703
+ "<|endoftext|>": 0.01837875189616327,
704
+ "l": 0.002329700944584073,
705
+ "m": 0.0012942783025467082,
706
+ "w": 0.0015531339630560485,
707
+ "s": 0.001811989623565391,
708
+ "n": 0.0005177113210186822,
709
+ "y": 0.0025885566050934164,
710
+ "v": 0.0012942783025467082,
711
+ "k": 0.0005177113210186822,
712
+ "j": 0.0005177113210186822,
713
+ "d": 0.0010354226420373645,
714
+ "c": 0.0010354226420373645,
715
+ "t": 0.0005177113210186822,
716
+ "p": 0.0002588556605093411,
717
+ "b": 0.0002588556605093411
718
+ }
719
+ },
720
+ "harmonic_seed": 1251963776,
721
+ "harmonic_frequencies": [
722
+ 1,
723
+ 1.618033988749895,
724
+ 2,
725
+ 3.141592653589793
726
+ ],
727
+ "config": {
728
+ "grpo": {
729
+ "group_size": 8,
730
+ "kl_penalty": 0.1
731
+ },
732
+ "vae": {
733
+ "latent_dim": 32,
734
+ "filter_threshold": 0.7
735
+ },
736
+ "policy_arch": "tiny-bigram"
737
+ },
738
+ "metrics": {
739
+ "training_steps": 60,
740
+ "final_loss": 0.020151837338568165,
741
+ "average_reward": 0.9016666666666666
742
+ }
743
+ }
requirements.txt ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ # Core test.py requires only Python 3.8+ standard library.
2
+ # Optional:
3
+ pandas>=2.0
4
+ pyarrow>=14.0
run.sh ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env bash
2
+ # run.sh - Minimal launcher for test.py.
3
+ set -euo pipefail
4
+ cd "$(dirname "$0")"
5
+ PY="${PYTHON:-python3}"
6
+ if ! command -v "$PY" >/dev/null 2>&1; then
7
+ echo "Error: python3 not found." >&2
8
+ exit 1
9
+ fi
10
+ exec "$PY" test.py "$@"
test.py ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python3
2
+ """
3
+ test.py - Micro Distillery model chat wrapper.
4
+
5
+ Loads model.json (a GRPO+VAE-distilled bigram model) and provides
6
+ a simple REPL chat interface.
7
+
8
+ Usage:
9
+ python3 test.py # interactive chat
10
+ python3 test.py hello # one-shot from prompt
11
+ python3 test.py --temperature 1.2 # one-shot with custom temperature
12
+ python3 test.py # (interactive also supports --temperature)
13
+ """
14
+ import json
15
+ import os
16
+ import random
17
+ import sys
18
+
19
+ MODEL_PATH = os.path.join(os.path.dirname(os.path.abspath(__file__)), "model.json")
20
+
21
+
22
+ def load_model(path=MODEL_PATH):
23
+ with open(path, "r", encoding="utf-8") as f:
24
+ return json.load(f)
25
+
26
+
27
+ def sample_next(transitions, token, rng, temperature=1.0):
28
+ bucket = transitions.get(token)
29
+ if not bucket:
30
+ return None
31
+ tokens = list(bucket.keys())
32
+ inv_t = 1.0 / max(temperature, 1e-3)
33
+ weights = [max(bucket[t], 1e-12) ** inv_t for t in tokens]
34
+ total = sum(weights)
35
+ if total <= 0:
36
+ return None
37
+ r = rng.random() * total
38
+ acc = 0.0
39
+ for t, w in zip(tokens, weights):
40
+ acc += w
41
+ if r <= acc:
42
+ return t
43
+ return tokens[-1]
44
+
45
+
46
+ def generate(model, prompt, max_tokens=32, temperature=0.9):
47
+ transitions = model.get("transitions", {})
48
+ bos = model.get("bos_token", "<|endoftext|>")
49
+ eos = model.get("eos_token", "<|endoftext|>")
50
+ seed = int(model.get("harmonic_seed", 1337)) & 0xFFFFFFFF
51
+ rng = random.Random(seed)
52
+
53
+ if prompt and prompt.strip():
54
+ current = prompt.strip()[-1]
55
+ prefix = prompt.strip()
56
+ else:
57
+ current = bos
58
+ prefix = ""
59
+
60
+ generated = ""
61
+ for _ in range(max_tokens):
62
+ nxt = sample_next(transitions, current, rng, temperature=temperature)
63
+ if nxt is None or nxt == eos:
64
+ break
65
+ generated += nxt
66
+ current = nxt
67
+ return prefix + generated
68
+
69
+
70
+ def main(temperature=0.9):
71
+ print("=== Micro Distillery Model Chat ===")
72
+ if not os.path.exists(MODEL_PATH):
73
+ print("Error: " + MODEL_PATH + " not found.", file=sys.stderr)
74
+ sys.exit(1)
75
+ model = load_model()
76
+ print("Format: " + str(model.get("format")))
77
+ print("Vocab size: " + str(len(model.get("vocab", []))))
78
+ print("Transitions: " + str(len(model.get("transitions", {}))))
79
+ print("Seed: " + str(model.get("harmonic_seed")))
80
+ print("Temperature: " + str(temperature))
81
+ print("Type /quit to exit.\n")
82
+ while True:
83
+ try:
84
+ prompt = input("You: ").strip()
85
+ except (EOFError, KeyboardInterrupt):
86
+ print("\nBye!")
87
+ break
88
+ if not prompt:
89
+ continue
90
+ if prompt.lower() in ("/quit", "/exit", "quit", "exit"):
91
+ break
92
+ out = generate(model, prompt, temperature=temperature)
93
+ print("Bot: " + out)
94
+
95
+
96
+ if __name__ == "__main__":
97
+ args = sys.argv[1:]
98
+ temperature = 0.9
99
+ prompts = []
100
+ i = 0
101
+ while i < len(args):
102
+ if args[i] == "--temperature":
103
+ if i + 1 < len(args):
104
+ try:
105
+ temperature = float(args[i + 1])
106
+ except ValueError:
107
+ print("Warning: invalid --temperature value, using 0.9", file=sys.stderr)
108
+ i += 2
109
+ else:
110
+ print("Warning: --temperature requires a value, using 0.9", file=sys.stderr)
111
+ i += 1
112
+ elif args[i] in ("--help", "-h"):
113
+ print("Usage: python3 test.py [prompt...] [--temperature T]")
114
+ sys.exit(0)
115
+ elif args[i].startswith("--"):
116
+ i += 1
117
+ else:
118
+ prompts.append(args[i])
119
+ i += 1
120
+ if prompts:
121
+ model = load_model()
122
+ print(generate(model, " ".join(prompts), temperature=temperature))
123
+ else:
124
+ main(temperature=temperature)
test.sh ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env bash
2
+ # test.sh - Test harness for the exported Micro Distillery model.
3
+ set -euo pipefail
4
+ cd "$(dirname "$0")"
5
+
6
+ PY="${PYTHON:-python3}"
7
+
8
+ echo "================================================"
9
+ echo " Micro Distillery - Model Test Harness"
10
+ echo "================================================"
11
+ echo ""
12
+
13
+ if ! command -v "$PY" >/dev/null 2>&1; then
14
+ echo "ERROR: $PY not found. Install Python 3.8+." >&2
15
+ echo " macOS: brew install python3" >&2
16
+ echo " Ubuntu: sudo apt install python3" >&2
17
+ echo " Windows: https://python.org/downloads/" >&2
18
+ exit 1
19
+ fi
20
+
21
+ echo "[1/3] Python: $($PY --version 2>&1)"
22
+
23
+ if [ ! -f model.json ]; then
24
+ echo "ERROR: model.json not found in $(pwd)" >&2
25
+ exit 1
26
+ fi
27
+ echo "[2/3] Found model.json"
28
+
29
+ $PY -c "
30
+ import json
31
+ m = json.load(open('model.json'))
32
+ assert 'transitions' in m, 'missing transitions'
33
+ assert 'vocab' in m, 'missing vocab'
34
+ print('OK: format=%s vocab=%d transitions=%d' % (m.get('format','?'), len(m['vocab']), len(m['transitions'])))
35
+ "
36
+ echo "[3/3] Model validation passed"
37
+ echo ""
38
+ echo "=== Sample Generations ==="
39
+ for prompt in alice bob zoe liam; do
40
+ echo -n " $prompt -> "
41
+ $PY test.py "$prompt" 2>/dev/null | tail -1 || echo "(failed)"
42
+ done
43
+ echo ""
44
+ echo "=== Interactive Chat (type /quit to exit) ==="
45
+ exec $PY test.py
test_readme.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Testing Your Exported Model
2
+
3
+ This bundle contains a fully runnable bigram language model. No GPU,
4
+ no external dependencies - Python 3.8+ standard library only.
5
+
6
+ ## Files
7
+
8
+ | File | Purpose |
9
+ |------|---------|
10
+ | `model.json` | The trained model (transitions + config + metrics) |
11
+ | `test.py` | Interactive chat wrapper |
12
+ | `test.sh` | Test harness (validates + generates samples) |
13
+ | `run.sh` | Minimal launcher for test.py |
14
+
15
+ ## Quick Start
16
+
17
+ ### macOS / Linux
18
+
19
+ ```bash
20
+ chmod +x test.sh run.sh
21
+ ./test.sh
22
+ ```
23
+
24
+ ### Windows (PowerShell)
25
+
26
+ ```powershell
27
+ python test.py
28
+ ```
29
+
30
+ ### One-shot generation
31
+
32
+ ```bash
33
+ python3 test.py alice
34
+ # => alice… (seed-dependent continuation)
35
+ ```
36
+
37
+ ### Custom temperature
38
+
39
+ ```bash
40
+ python3 test.py --temperature 0.5
41
+ python3 test.py alice --temperature 1.2
42
+ ```
43
+
44
+ ## Manual Test
45
+
46
+ ```bash
47
+ python3 -c "import json; m=json.load(open('model.json')); print(len(m['vocab']), 'tokens,', len(m['transitions']), 'states')"
48
+ ```
49
+
50
+ Expected output: `<N> tokens, <M> states`.
51
+
52
+ ## Troubleshooting
53
+
54
+ - **`python3 not found`** - install Python 3.8+ from https://python.org
55
+ - **`model.json not found`** - make sure you are inside the extracted directory
56
+ - **`Permission denied`** - run `chmod +x test.sh run.sh` first
to_parquet.py ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python3
2
+ """Convert model.json to model.parquet.
3
+
4
+ Requires: pandas, pyarrow
5
+ pip install pandas pyarrow
6
+ """
7
+ import json
8
+ import os
9
+ import sys
10
+
11
+ MODEL_PATH = os.path.join(os.path.dirname(os.path.abspath(__file__)), "model.json")
12
+ OUT_PATH = os.path.join(os.path.dirname(os.path.abspath(__file__)), "model.parquet")
13
+
14
+
15
+ def main():
16
+ try:
17
+ import pandas as pd
18
+ except ImportError:
19
+ print("Error: pandas required. Install: pip install pandas pyarrow", file=sys.stderr)
20
+ sys.exit(1)
21
+
22
+ with open(MODEL_PATH, "r", encoding="utf-8") as f:
23
+ model = json.load(f)
24
+
25
+ rows = []
26
+ for state, bucket in model.get("transitions", {}).items():
27
+ for nxt, prob in bucket.items():
28
+ rows.append({
29
+ "state": state,
30
+ "next_token": nxt,
31
+ "probability": float(prob),
32
+ "harmonic_seed": int(model.get("harmonic_seed", 0)),
33
+ "format": model.get("format", "unknown"),
34
+ "version": model.get("version", "0.0"),
35
+ })
36
+
37
+ if not rows:
38
+ print("Warning: no transitions. Writing metadata-only parquet.")
39
+ rows = [{"state": "", "next_token": "", "probability": 0.0,
40
+ "harmonic_seed": int(model.get("harmonic_seed", 0)),
41
+ "format": model.get("format", "unknown"),
42
+ "version": model.get("version", "0.0")}]
43
+
44
+ df = pd.DataFrame(rows)
45
+ df.to_parquet(OUT_PATH, index=False)
46
+ print("Wrote " + str(len(df)) + " rows to " + OUT_PATH)
47
+
48
+
49
+ if __name__ == "__main__":
50
+ main()
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "PreTrainedTokenizerFast",
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>",
6
+ "pad_token": "<|endoftext|>",
7
+ "add_prefix_space": false,
8
+ "model_max_length": 1024,
9
+ "name_or_path": "micro-distillery"
10
+ }
training_logs.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "created": "2026-10-23T16:28:35.871Z",
3
+ "metrics": {
4
+ "trainingSteps": 60,
5
+ "finalLoss": 0.020151837338568165,
6
+ "averageReward": 0.9016666666666666,
7
+ "cacheHits": 3,
8
+ "cacheMisses": 250,
9
+ "filteredCount": 0,
10
+ "totalSamples": 0,
11
+ "vaeLoss": 0
12
+ },
13
+ "quantum_measurements": [
14
+ {
15
+ "oscillator": 0,
16
+ "energy": 0.5,
17
+ "x": 0.615234375,
18
+ "t": 0.1,
19
+ "probabilities": [
20
+ 0.25,
21
+ 0.25,
22
+ 0.25,
23
+ 0.25
24
+ ]
25
+ },
26
+ {
27
+ "oscillator": 3,
28
+ "energy": 10.995574287564276,
29
+ "x": -1.1074424442685453,
30
+ "t": 0.2,
31
+ "probabilities": [
32
+ 0.25,
33
+ 0.25,
34
+ 0.25,
35
+ 0.25
36
+ ]
37
+ },
38
+ {
39
+ "oscillator": 3,
40
+ "energy": 10.995574287564276,
41
+ "x": 0.23140588387700944,
42
+ "t": 0.30000000000000004,
43
+ "probabilities": [
44
+ 0.24999999999999997,
45
+ 0.25,
46
+ 0.24999999999999997,
47
+ 0.25
48
+ ]
49
+ },
50
+ {
51
+ "oscillator": 1,
52
+ "energy": 2.4270509831248424,
53
+ "x": -0.7830804739380586,
54
+ "t": 0.4,
55
+ "probabilities": [
56
+ 0.25,
57
+ 0.25,
58
+ 0.25,
59
+ 0.24999999999999997
60
+ ]
61
+ },
62
+ {
63
+ "oscillator": 3,
64
+ "energy": 10.995574287564276,
65
+ "x": -0.2644638672880113,
66
+ "t": 0.5,
67
+ "probabilities": [
68
+ 0.24999999999999997,
69
+ 0.25,
70
+ 0.25,
71
+ 0.25
72
+ ]
73
+ },
74
+ {
75
+ "oscillator": 3,
76
+ "energy": 10.995574287564276,
77
+ "x": 1.7355441290775708,
78
+ "t": 0.6,
79
+ "probabilities": [
80
+ 0.25,
81
+ 0.25,
82
+ 0.25,
83
+ 0.25
84
+ ]
85
+ },
86
+ {
87
+ "oscillator": 0,
88
+ "energy": 0.5,
89
+ "x": 1.171875,
90
+ "t": 0.7,
91
+ "probabilities": [
92
+ 0.25,
93
+ 0.25,
94
+ 0.25,
95
+ 0.25
96
+ ]
97
+ },
98
+ {
99
+ "oscillator": 3,
100
+ "energy": 10.995574287564276,
101
+ "x": -0.34710882581551417,
102
+ "t": 0.7999999999999999,
103
+ "probabilities": [
104
+ 0.25,
105
+ 0.25,
106
+ 0.25,
107
+ 0.25
108
+ ]
109
+ }
110
+ ],
111
+ "config": {
112
+ "grpo": {
113
+ "group_size": 8,
114
+ "kl_penalty": 0.1
115
+ },
116
+ "vae": {
117
+ "latent_dim": 32,
118
+ "filter_threshold": 0.7
119
+ },
120
+ "policy_arch": "tiny-bigram"
121
+ }
122
+ }
vocab.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "e": 0,
3
+ "m": 1,
4
+ "a": 2,
5
+ "<|endoftext|>": 3,
6
+ "o": 4,
7
+ "l": 5,
8
+ "i": 6,
9
+ "v": 7,
10
+ "s": 8,
11
+ "b": 9,
12
+ "p": 10,
13
+ "h": 11,
14
+ "c": 12,
15
+ "r": 13,
16
+ "t": 14,
17
+ "y": 15,
18
+ "n": 16,
19
+ "g": 17,
20
+ "z": 18,
21
+ "f": 19,
22
+ "d": 20,
23
+ "u": 21,
24
+ "k": 22,
25
+ "w": 23,
26
+ "q": 24,
27
+ "x": 25,
28
+ "j": 26
29
+ }