Upload structure model checkpoint at step 4000
Browse files- checkpoint_4000/README.md +46 -0
- checkpoint_4000/config.json +14 -0
- checkpoint_4000/model.npz +3 -0
- checkpoint_4000/training_state.json +223 -0
checkpoint_4000/README.md
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: mlx
|
3 |
+
pipeline_tag: text-generation
|
4 |
+
tags:
|
5 |
+
- music
|
6 |
+
- midi
|
7 |
+
- generation
|
8 |
+
- mlx
|
9 |
+
- autoregressive
|
10 |
+
- structure
|
11 |
+
- musiclang
|
12 |
+
---
|
13 |
+
|
14 |
+
# okai-musiclang-structure v2.0 - Structure Model
|
15 |
+
|
16 |
+
This is an autoregressive structure generation model for music using MLX.
|
17 |
+
|
18 |
+
## Model Details
|
19 |
+
|
20 |
+
- **Model Type**: Structure Generator (Autoregressive)
|
21 |
+
- **Version**: v2.0
|
22 |
+
- **Step**: 4000
|
23 |
+
- **Architecture**: Transformer with causal language modeling
|
24 |
+
- **Vocabulary Size**: 4796
|
25 |
+
- **Model Dimension**: 256
|
26 |
+
- **Layers**: 6
|
27 |
+
- **Max Sequence Length**: 1024
|
28 |
+
|
29 |
+
## Training Configuration
|
30 |
+
|
31 |
+
- **Batch Size**: 16
|
32 |
+
- **Learning Rate**: 1e-05
|
33 |
+
- **Training Steps**: 4000
|
34 |
+
|
35 |
+
## Usage
|
36 |
+
|
37 |
+
This model generates sequential music structure:
|
38 |
+
- Input: Song control tokens (genre, instruments, etc.)
|
39 |
+
- Output: Sequential bar structure with chords and tonality
|
40 |
+
|
41 |
+
Example generation:
|
42 |
+
```
|
43 |
+
GENRE__ROCK SUBGENRE__ALTERNATIVE START BAR__1 CHORD_DEGREE__1 TONALITY_DEGREE__1 BAR__2 CHORD_DEGREE__4 TONALITY_DEGREE__5 ... WILL_END
|
44 |
+
```
|
45 |
+
|
46 |
+
Generated with MLX framework for Apple Silicon.
|
checkpoint_4000/config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_name": "okai-musiclang-structure",
|
3 |
+
"model_version": "v2.0",
|
4 |
+
"model_type": "structure",
|
5 |
+
"global_step": 4000,
|
6 |
+
"architecture": "AutoregressiveTransformer",
|
7 |
+
"training_type": "causal_lm",
|
8 |
+
"vocab_size": 4796,
|
9 |
+
"model_dim": 256,
|
10 |
+
"num_heads": 8,
|
11 |
+
"num_layers": 6,
|
12 |
+
"max_sequence_length": 1024,
|
13 |
+
"dropout": 0.1
|
14 |
+
}
|
checkpoint_4000/model.npz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2b59c90bc84366a35e1f35efb90569de1942d7f1d71d16fc73b235b6121d7c6
|
3 |
+
size 29839884
|
checkpoint_4000/training_state.json
ADDED
@@ -0,0 +1,223 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"global_step": 4000,
|
3 |
+
"epoch": 2,
|
4 |
+
"trainer_step": 4000,
|
5 |
+
"learning_rate": 9.999999747378752e-06,
|
6 |
+
"epoch_losses": [
|
7 |
+
0.9623835682868958,
|
8 |
+
0.9403253197669983,
|
9 |
+
1.1018129587173462,
|
10 |
+
1.099521517753601,
|
11 |
+
1.1239317655563354,
|
12 |
+
1.005245566368103,
|
13 |
+
1.049521803855896,
|
14 |
+
0.973974883556366,
|
15 |
+
0.9835813641548157,
|
16 |
+
1.1106715202331543,
|
17 |
+
0.9983314275741577,
|
18 |
+
0.9675887227058411,
|
19 |
+
0.9586872458457947,
|
20 |
+
1.0531725883483887,
|
21 |
+
0.9274307489395142,
|
22 |
+
0.8881500959396362,
|
23 |
+
0.9156804084777832,
|
24 |
+
0.9054280519485474,
|
25 |
+
0.9903623461723328,
|
26 |
+
1.085747480392456,
|
27 |
+
0.9666320085525513,
|
28 |
+
1.0550706386566162,
|
29 |
+
1.0309563875198364,
|
30 |
+
1.0470917224884033,
|
31 |
+
1.2648228406906128,
|
32 |
+
1.058887243270874,
|
33 |
+
1.0034480094909668,
|
34 |
+
0.9759008884429932,
|
35 |
+
0.9830622673034668,
|
36 |
+
1.0078848600387573,
|
37 |
+
1.106107473373413,
|
38 |
+
0.9574833512306213,
|
39 |
+
1.0131721496582031,
|
40 |
+
1.0299617052078247,
|
41 |
+
1.1269416809082031,
|
42 |
+
1.1237963438034058,
|
43 |
+
1.081311583518982,
|
44 |
+
1.0172157287597656,
|
45 |
+
0.9460458755493164,
|
46 |
+
1.0029174089431763,
|
47 |
+
0.9555768966674805,
|
48 |
+
1.0631312131881714,
|
49 |
+
1.0947638750076294,
|
50 |
+
1.0890942811965942,
|
51 |
+
0.9915012717247009,
|
52 |
+
1.0350689888000488,
|
53 |
+
0.957879900932312,
|
54 |
+
1.0205248594284058,
|
55 |
+
0.9791820645332336,
|
56 |
+
1.0714317560195923,
|
57 |
+
1.0099210739135742,
|
58 |
+
0.9102389812469482,
|
59 |
+
0.9683911800384521,
|
60 |
+
1.0109338760375977,
|
61 |
+
0.9437877535820007,
|
62 |
+
0.9779325127601624,
|
63 |
+
1.0287659168243408,
|
64 |
+
0.9966862797737122,
|
65 |
+
0.9972357153892517,
|
66 |
+
1.0247901678085327,
|
67 |
+
0.8865885734558105,
|
68 |
+
0.9496268033981323,
|
69 |
+
1.1149026155471802,
|
70 |
+
0.9584646224975586,
|
71 |
+
1.039094090461731,
|
72 |
+
0.9983192682266235,
|
73 |
+
0.9523110389709473,
|
74 |
+
0.9627136588096619,
|
75 |
+
1.0479315519332886,
|
76 |
+
1.014502763748169,
|
77 |
+
1.047270655632019,
|
78 |
+
0.9777000546455383,
|
79 |
+
1.0754557847976685,
|
80 |
+
1.0394912958145142,
|
81 |
+
1.0451149940490723,
|
82 |
+
0.9772164225578308,
|
83 |
+
0.879372775554657,
|
84 |
+
1.0176762342453003,
|
85 |
+
1.1346173286437988,
|
86 |
+
1.065199375152588,
|
87 |
+
0.9794224500656128,
|
88 |
+
0.994093120098114,
|
89 |
+
1.080609679222107,
|
90 |
+
1.0241132974624634,
|
91 |
+
0.9821677803993225,
|
92 |
+
1.0236629247665405,
|
93 |
+
1.0970886945724487,
|
94 |
+
0.9859799146652222,
|
95 |
+
1.0206303596496582,
|
96 |
+
0.963985800743103,
|
97 |
+
1.1415214538574219,
|
98 |
+
0.9476262927055359,
|
99 |
+
0.9723619222640991,
|
100 |
+
1.0430418252944946,
|
101 |
+
0.9370524883270264,
|
102 |
+
1.1020606756210327,
|
103 |
+
0.9914152026176453,
|
104 |
+
0.9265563488006592,
|
105 |
+
0.9476118683815002,
|
106 |
+
1.0010508298873901,
|
107 |
+
0.9700972437858582,
|
108 |
+
0.9239491820335388,
|
109 |
+
0.9755258560180664,
|
110 |
+
1.0607982873916626,
|
111 |
+
1.0430976152420044,
|
112 |
+
1.0094655752182007,
|
113 |
+
0.9351859092712402,
|
114 |
+
1.0080362558364868,
|
115 |
+
1.0132410526275635,
|
116 |
+
0.99669349193573,
|
117 |
+
1.0678595304489136,
|
118 |
+
0.9482328295707703,
|
119 |
+
1.102686882019043,
|
120 |
+
0.9091104865074158,
|
121 |
+
0.9526283144950867,
|
122 |
+
1.0539052486419678,
|
123 |
+
0.9654752016067505,
|
124 |
+
0.9763954877853394,
|
125 |
+
0.9747753143310547,
|
126 |
+
0.916806697845459,
|
127 |
+
1.0926268100738525,
|
128 |
+
0.9755257368087769,
|
129 |
+
0.9996986389160156,
|
130 |
+
0.8870878219604492,
|
131 |
+
0.9472292065620422,
|
132 |
+
0.9068527817726135,
|
133 |
+
0.9669629335403442,
|
134 |
+
0.9846920967102051,
|
135 |
+
0.9890540838241577,
|
136 |
+
0.9239402413368225,
|
137 |
+
0.9894418716430664,
|
138 |
+
0.9652270674705505,
|
139 |
+
0.9375078082084656,
|
140 |
+
0.9628201127052307,
|
141 |
+
1.0383803844451904,
|
142 |
+
1.1081637144088745,
|
143 |
+
0.9401895999908447,
|
144 |
+
0.9985557198524475,
|
145 |
+
1.0413312911987305,
|
146 |
+
0.9907352924346924,
|
147 |
+
1.0869688987731934,
|
148 |
+
0.9816573858261108,
|
149 |
+
1.018790364265442,
|
150 |
+
0.956809937953949,
|
151 |
+
1.0393168926239014,
|
152 |
+
0.9685669541358948,
|
153 |
+
1.0792640447616577,
|
154 |
+
0.8656201958656311,
|
155 |
+
1.064882755279541,
|
156 |
+
1.0167142152786255,
|
157 |
+
0.9906323552131653,
|
158 |
+
0.9442341327667236,
|
159 |
+
1.129238247871399,
|
160 |
+
0.9736506342887878,
|
161 |
+
0.9243375062942505,
|
162 |
+
0.9149096012115479,
|
163 |
+
0.9671629071235657,
|
164 |
+
1.0616192817687988,
|
165 |
+
0.9195281863212585,
|
166 |
+
0.9835683107376099,
|
167 |
+
1.002117395401001,
|
168 |
+
1.04807710647583,
|
169 |
+
0.948814332485199,
|
170 |
+
1.054269790649414,
|
171 |
+
0.9761651158332825,
|
172 |
+
0.9554536938667297,
|
173 |
+
1.0568958520889282,
|
174 |
+
0.9930166006088257,
|
175 |
+
1.0983678102493286,
|
176 |
+
1.1102592945098877,
|
177 |
+
0.979726254940033,
|
178 |
+
0.9644660353660583,
|
179 |
+
1.034118413925171,
|
180 |
+
1.0168700218200684,
|
181 |
+
1.0164395570755005,
|
182 |
+
0.9126317501068115,
|
183 |
+
1.0128051042556763,
|
184 |
+
0.9272709488868713,
|
185 |
+
0.9970700740814209,
|
186 |
+
0.9975913166999817,
|
187 |
+
0.9783541560173035,
|
188 |
+
1.0276747941970825,
|
189 |
+
0.8939880132675171,
|
190 |
+
0.9969168305397034,
|
191 |
+
0.9142337441444397,
|
192 |
+
0.9654040336608887,
|
193 |
+
0.9739183187484741,
|
194 |
+
1.01646089553833,
|
195 |
+
1.037825107574463,
|
196 |
+
0.9719421863555908,
|
197 |
+
0.9977736473083496,
|
198 |
+
0.9816113114356995,
|
199 |
+
0.9727272987365723,
|
200 |
+
0.9714145660400391
|
201 |
+
],
|
202 |
+
"training_config": {
|
203 |
+
"batch_size": 16,
|
204 |
+
"num_epochs": 4,
|
205 |
+
"learning_rate": 1e-05,
|
206 |
+
"weight_decay": 0.01,
|
207 |
+
"warmup_steps": 1000,
|
208 |
+
"max_grad_norm": 1.0,
|
209 |
+
"eval_steps": 500,
|
210 |
+
"save_steps": 500
|
211 |
+
},
|
212 |
+
"model_config": {
|
213 |
+
"vocab_size": 4796,
|
214 |
+
"model_dim": 256,
|
215 |
+
"num_heads": 8,
|
216 |
+
"num_layers": 6,
|
217 |
+
"max_sequence_length": 1024,
|
218 |
+
"dropout": 0.1
|
219 |
+
},
|
220 |
+
"model_name": "okai-musiclang-structure",
|
221 |
+
"model_version": "v2.0",
|
222 |
+
"model_type": "structure"
|
223 |
+
}
|