Hugging Face's logo

harp-dev
/
music-spectrogram-diffusion-checkpoints

Model card Files
xet
 Community
harp-dev commited on
Commit
9572863
·
verified ·
1 Parent(s): ff822cc

Upload 1017 files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +334 -0
  2. checkpoint_500000/checkpoint +3 -0
  3. checkpoint_500000/state.param_states.continuous_encoder.encoder_norm.scale.v/.zarray +1 -0
  4. checkpoint_500000/state.param_states.continuous_encoder.encoder_norm.scale.v/0 +0 -0
  5. checkpoint_500000/state.param_states.continuous_encoder.layers_0.pre_attention_layer_norm.scale.v/.zarray +1 -0
  6. checkpoint_500000/state.param_states.continuous_encoder.layers_0.pre_attention_layer_norm.scale.v/0 +0 -0
  7. checkpoint_500000/state.param_states.continuous_encoder.layers_0.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  8. checkpoint_500000/state.param_states.continuous_encoder.layers_0.pre_mlp_layer_norm.scale.v/0 +0 -0
  9. checkpoint_500000/state.param_states.continuous_encoder.layers_1.pre_attention_layer_norm.scale.v/.zarray +1 -0
  10. checkpoint_500000/state.param_states.continuous_encoder.layers_1.pre_attention_layer_norm.scale.v/0 +0 -0
  11. checkpoint_500000/state.param_states.continuous_encoder.layers_1.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  12. checkpoint_500000/state.param_states.continuous_encoder.layers_1.pre_mlp_layer_norm.scale.v/0 +0 -0
  13. checkpoint_500000/state.param_states.continuous_encoder.layers_10.pre_attention_layer_norm.scale.v/.zarray +1 -0
  14. checkpoint_500000/state.param_states.continuous_encoder.layers_10.pre_attention_layer_norm.scale.v/0 +0 -0
  15. checkpoint_500000/state.param_states.continuous_encoder.layers_10.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  16. checkpoint_500000/state.param_states.continuous_encoder.layers_10.pre_mlp_layer_norm.scale.v/0 +0 -0
  17. checkpoint_500000/state.param_states.continuous_encoder.layers_11.pre_attention_layer_norm.scale.v/.zarray +1 -0
  18. checkpoint_500000/state.param_states.continuous_encoder.layers_11.pre_attention_layer_norm.scale.v/0 +0 -0
  19. checkpoint_500000/state.param_states.continuous_encoder.layers_11.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  20. checkpoint_500000/state.param_states.continuous_encoder.layers_11.pre_mlp_layer_norm.scale.v/0 +0 -0
  21. checkpoint_500000/state.param_states.continuous_encoder.layers_2.pre_attention_layer_norm.scale.v/.zarray +1 -0
  22. checkpoint_500000/state.param_states.continuous_encoder.layers_2.pre_attention_layer_norm.scale.v/0 +0 -0
  23. checkpoint_500000/state.param_states.continuous_encoder.layers_2.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  24. checkpoint_500000/state.param_states.continuous_encoder.layers_2.pre_mlp_layer_norm.scale.v/0 +0 -0
  25. checkpoint_500000/state.param_states.continuous_encoder.layers_3.pre_attention_layer_norm.scale.v/.zarray +1 -0
  26. checkpoint_500000/state.param_states.continuous_encoder.layers_3.pre_attention_layer_norm.scale.v/0 +0 -0
  27. checkpoint_500000/state.param_states.continuous_encoder.layers_3.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  28. checkpoint_500000/state.param_states.continuous_encoder.layers_3.pre_mlp_layer_norm.scale.v/0 +0 -0
  29. checkpoint_500000/state.param_states.continuous_encoder.layers_4.pre_attention_layer_norm.scale.v/.zarray +1 -0
  30. checkpoint_500000/state.param_states.continuous_encoder.layers_4.pre_attention_layer_norm.scale.v/0 +0 -0
  31. checkpoint_500000/state.param_states.continuous_encoder.layers_4.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  32. checkpoint_500000/state.param_states.continuous_encoder.layers_4.pre_mlp_layer_norm.scale.v/0 +0 -0
  33. checkpoint_500000/state.param_states.continuous_encoder.layers_5.pre_attention_layer_norm.scale.v/.zarray +1 -0
  34. checkpoint_500000/state.param_states.continuous_encoder.layers_5.pre_attention_layer_norm.scale.v/0 +0 -0
  35. checkpoint_500000/state.param_states.continuous_encoder.layers_5.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  36. checkpoint_500000/state.param_states.continuous_encoder.layers_5.pre_mlp_layer_norm.scale.v/0 +0 -0
  37. checkpoint_500000/state.param_states.continuous_encoder.layers_6.pre_attention_layer_norm.scale.v/.zarray +1 -0
  38. checkpoint_500000/state.param_states.continuous_encoder.layers_6.pre_attention_layer_norm.scale.v/0 +0 -0
  39. checkpoint_500000/state.param_states.continuous_encoder.layers_6.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  40. checkpoint_500000/state.param_states.continuous_encoder.layers_6.pre_mlp_layer_norm.scale.v/0 +0 -0
  41. checkpoint_500000/state.param_states.continuous_encoder.layers_7.pre_attention_layer_norm.scale.v/.zarray +1 -0
  42. checkpoint_500000/state.param_states.continuous_encoder.layers_7.pre_attention_layer_norm.scale.v/0 +0 -0
  43. checkpoint_500000/state.param_states.continuous_encoder.layers_7.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  44. checkpoint_500000/state.param_states.continuous_encoder.layers_7.pre_mlp_layer_norm.scale.v/0 +0 -0
  45. checkpoint_500000/state.param_states.continuous_encoder.layers_8.pre_attention_layer_norm.scale.v/.zarray +1 -0
  46. checkpoint_500000/state.param_states.continuous_encoder.layers_8.pre_attention_layer_norm.scale.v/0 +0 -0
  47. checkpoint_500000/state.param_states.continuous_encoder.layers_8.pre_mlp_layer_norm.scale.v/.zarray +1 -0
  48. checkpoint_500000/state.param_states.continuous_encoder.layers_8.pre_mlp_layer_norm.scale.v/0 +0 -0
  49. checkpoint_500000/state.param_states.continuous_encoder.layers_9.pre_attention_layer_norm.scale.v/.zarray +1 -0
  50. checkpoint_500000/state.param_states.continuous_encoder.layers_9.pre_attention_layer_norm.scale.v/0 +0 -0
.gitattributes CHANGED
@@ -33,3 +33,337 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint_500000/checkpoint filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint_500000/target.continuous_encoder.Embed_0.embedding/0.0 filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint_500000/target.continuous_encoder.input_proj.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint_500000/target.continuous_encoder.layers_0.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint_500000/target.continuous_encoder.layers_0.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
41
+ checkpoint_500000/target.continuous_encoder.layers_0.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
42
+ checkpoint_500000/target.continuous_encoder.layers_0.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
43
+ checkpoint_500000/target.continuous_encoder.layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
44
+ checkpoint_500000/target.continuous_encoder.layers_0.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
45
+ checkpoint_500000/target.continuous_encoder.layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
46
+ checkpoint_500000/target.continuous_encoder.layers_1.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
47
+ checkpoint_500000/target.continuous_encoder.layers_1.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
48
+ checkpoint_500000/target.continuous_encoder.layers_1.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
49
+ checkpoint_500000/target.continuous_encoder.layers_1.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
50
+ checkpoint_500000/target.continuous_encoder.layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
51
+ checkpoint_500000/target.continuous_encoder.layers_1.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
52
+ checkpoint_500000/target.continuous_encoder.layers_1.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
53
+ checkpoint_500000/target.continuous_encoder.layers_10.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
54
+ checkpoint_500000/target.continuous_encoder.layers_10.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
55
+ checkpoint_500000/target.continuous_encoder.layers_10.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
56
+ checkpoint_500000/target.continuous_encoder.layers_10.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
57
+ checkpoint_500000/target.continuous_encoder.layers_10.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
58
+ checkpoint_500000/target.continuous_encoder.layers_10.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
59
+ checkpoint_500000/target.continuous_encoder.layers_10.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
60
+ checkpoint_500000/target.continuous_encoder.layers_11.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
61
+ checkpoint_500000/target.continuous_encoder.layers_11.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
62
+ checkpoint_500000/target.continuous_encoder.layers_11.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
63
+ checkpoint_500000/target.continuous_encoder.layers_11.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
64
+ checkpoint_500000/target.continuous_encoder.layers_11.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
65
+ checkpoint_500000/target.continuous_encoder.layers_11.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
66
+ checkpoint_500000/target.continuous_encoder.layers_11.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
67
+ checkpoint_500000/target.continuous_encoder.layers_2.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
68
+ checkpoint_500000/target.continuous_encoder.layers_2.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
69
+ checkpoint_500000/target.continuous_encoder.layers_2.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
70
+ checkpoint_500000/target.continuous_encoder.layers_2.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
71
+ checkpoint_500000/target.continuous_encoder.layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
72
+ checkpoint_500000/target.continuous_encoder.layers_2.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
73
+ checkpoint_500000/target.continuous_encoder.layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
74
+ checkpoint_500000/target.continuous_encoder.layers_3.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
75
+ checkpoint_500000/target.continuous_encoder.layers_3.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
76
+ checkpoint_500000/target.continuous_encoder.layers_3.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
77
+ checkpoint_500000/target.continuous_encoder.layers_3.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
78
+ checkpoint_500000/target.continuous_encoder.layers_3.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
79
+ checkpoint_500000/target.continuous_encoder.layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
80
+ checkpoint_500000/target.continuous_encoder.layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
81
+ checkpoint_500000/target.continuous_encoder.layers_4.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
82
+ checkpoint_500000/target.continuous_encoder.layers_4.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
83
+ checkpoint_500000/target.continuous_encoder.layers_4.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
84
+ checkpoint_500000/target.continuous_encoder.layers_4.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
85
+ checkpoint_500000/target.continuous_encoder.layers_4.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
86
+ checkpoint_500000/target.continuous_encoder.layers_4.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
87
+ checkpoint_500000/target.continuous_encoder.layers_4.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
88
+ checkpoint_500000/target.continuous_encoder.layers_5.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
89
+ checkpoint_500000/target.continuous_encoder.layers_5.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
90
+ checkpoint_500000/target.continuous_encoder.layers_5.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
91
+ checkpoint_500000/target.continuous_encoder.layers_5.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
92
+ checkpoint_500000/target.continuous_encoder.layers_5.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
93
+ checkpoint_500000/target.continuous_encoder.layers_5.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
94
+ checkpoint_500000/target.continuous_encoder.layers_5.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
95
+ checkpoint_500000/target.continuous_encoder.layers_6.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
96
+ checkpoint_500000/target.continuous_encoder.layers_6.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
97
+ checkpoint_500000/target.continuous_encoder.layers_6.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
98
+ checkpoint_500000/target.continuous_encoder.layers_6.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
99
+ checkpoint_500000/target.continuous_encoder.layers_6.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
100
+ checkpoint_500000/target.continuous_encoder.layers_6.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
101
+ checkpoint_500000/target.continuous_encoder.layers_6.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
102
+ checkpoint_500000/target.continuous_encoder.layers_7.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
103
+ checkpoint_500000/target.continuous_encoder.layers_7.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
104
+ checkpoint_500000/target.continuous_encoder.layers_7.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
105
+ checkpoint_500000/target.continuous_encoder.layers_7.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
106
+ checkpoint_500000/target.continuous_encoder.layers_7.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
107
+ checkpoint_500000/target.continuous_encoder.layers_7.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
108
+ checkpoint_500000/target.continuous_encoder.layers_7.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
109
+ checkpoint_500000/target.continuous_encoder.layers_8.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
110
+ checkpoint_500000/target.continuous_encoder.layers_8.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
111
+ checkpoint_500000/target.continuous_encoder.layers_8.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
112
+ checkpoint_500000/target.continuous_encoder.layers_8.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
113
+ checkpoint_500000/target.continuous_encoder.layers_8.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
114
+ checkpoint_500000/target.continuous_encoder.layers_8.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
115
+ checkpoint_500000/target.continuous_encoder.layers_8.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
116
+ checkpoint_500000/target.continuous_encoder.layers_9.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
117
+ checkpoint_500000/target.continuous_encoder.layers_9.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
118
+ checkpoint_500000/target.continuous_encoder.layers_9.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
119
+ checkpoint_500000/target.continuous_encoder.layers_9.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
120
+ checkpoint_500000/target.continuous_encoder.layers_9.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
121
+ checkpoint_500000/target.continuous_encoder.layers_9.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
122
+ checkpoint_500000/target.continuous_encoder.layers_9.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
123
+ checkpoint_500000/target.decoder.continuous_inputs_projection.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
124
+ checkpoint_500000/target.decoder.Embed_0.embedding/0.0 filter=lfs diff=lfs merge=lfs -text
125
+ checkpoint_500000/target.decoder.layers_0.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
126
+ checkpoint_500000/target.decoder.layers_0.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
127
+ checkpoint_500000/target.decoder.layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
128
+ checkpoint_500000/target.decoder.layers_0.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
129
+ checkpoint_500000/target.decoder.layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
130
+ checkpoint_500000/target.decoder.layers_0.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
131
+ checkpoint_500000/target.decoder.layers_0.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
132
+ checkpoint_500000/target.decoder.layers_0.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
133
+ checkpoint_500000/target.decoder.layers_0.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
134
+ checkpoint_500000/target.decoder.layers_0.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
135
+ checkpoint_500000/target.decoder.layers_0.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
136
+ checkpoint_500000/target.decoder.layers_0.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
137
+ checkpoint_500000/target.decoder.layers_0.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
138
+ checkpoint_500000/target.decoder.layers_1.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
139
+ checkpoint_500000/target.decoder.layers_1.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
140
+ checkpoint_500000/target.decoder.layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
141
+ checkpoint_500000/target.decoder.layers_1.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
142
+ checkpoint_500000/target.decoder.layers_1.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
143
+ checkpoint_500000/target.decoder.layers_1.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
144
+ checkpoint_500000/target.decoder.layers_1.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
145
+ checkpoint_500000/target.decoder.layers_1.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
146
+ checkpoint_500000/target.decoder.layers_1.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
147
+ checkpoint_500000/target.decoder.layers_1.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
148
+ checkpoint_500000/target.decoder.layers_1.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
149
+ checkpoint_500000/target.decoder.layers_1.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
150
+ checkpoint_500000/target.decoder.layers_1.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
151
+ checkpoint_500000/target.decoder.layers_10.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
152
+ checkpoint_500000/target.decoder.layers_10.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
153
+ checkpoint_500000/target.decoder.layers_10.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
154
+ checkpoint_500000/target.decoder.layers_10.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
155
+ checkpoint_500000/target.decoder.layers_10.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
156
+ checkpoint_500000/target.decoder.layers_10.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
157
+ checkpoint_500000/target.decoder.layers_10.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
158
+ checkpoint_500000/target.decoder.layers_10.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
159
+ checkpoint_500000/target.decoder.layers_10.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
160
+ checkpoint_500000/target.decoder.layers_10.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
161
+ checkpoint_500000/target.decoder.layers_10.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
162
+ checkpoint_500000/target.decoder.layers_10.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
163
+ checkpoint_500000/target.decoder.layers_10.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
164
+ checkpoint_500000/target.decoder.layers_11.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
165
+ checkpoint_500000/target.decoder.layers_11.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
166
+ checkpoint_500000/target.decoder.layers_11.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
167
+ checkpoint_500000/target.decoder.layers_11.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
168
+ checkpoint_500000/target.decoder.layers_11.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
169
+ checkpoint_500000/target.decoder.layers_11.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
170
+ checkpoint_500000/target.decoder.layers_11.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
171
+ checkpoint_500000/target.decoder.layers_11.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
172
+ checkpoint_500000/target.decoder.layers_11.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
173
+ checkpoint_500000/target.decoder.layers_11.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
174
+ checkpoint_500000/target.decoder.layers_11.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
175
+ checkpoint_500000/target.decoder.layers_11.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
176
+ checkpoint_500000/target.decoder.layers_11.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
177
+ checkpoint_500000/target.decoder.layers_2.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
178
+ checkpoint_500000/target.decoder.layers_2.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
179
+ checkpoint_500000/target.decoder.layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
180
+ checkpoint_500000/target.decoder.layers_2.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
181
+ checkpoint_500000/target.decoder.layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
182
+ checkpoint_500000/target.decoder.layers_2.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
183
+ checkpoint_500000/target.decoder.layers_2.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
184
+ checkpoint_500000/target.decoder.layers_2.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
185
+ checkpoint_500000/target.decoder.layers_2.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
186
+ checkpoint_500000/target.decoder.layers_2.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
187
+ checkpoint_500000/target.decoder.layers_2.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
188
+ checkpoint_500000/target.decoder.layers_2.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
189
+ checkpoint_500000/target.decoder.layers_2.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
190
+ checkpoint_500000/target.decoder.layers_3.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
191
+ checkpoint_500000/target.decoder.layers_3.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
192
+ checkpoint_500000/target.decoder.layers_3.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
193
+ checkpoint_500000/target.decoder.layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
194
+ checkpoint_500000/target.decoder.layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
195
+ checkpoint_500000/target.decoder.layers_3.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
196
+ checkpoint_500000/target.decoder.layers_3.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
197
+ checkpoint_500000/target.decoder.layers_3.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
198
+ checkpoint_500000/target.decoder.layers_3.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
199
+ checkpoint_500000/target.decoder.layers_3.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
200
+ checkpoint_500000/target.decoder.layers_3.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
201
+ checkpoint_500000/target.decoder.layers_3.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
202
+ checkpoint_500000/target.decoder.layers_3.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
203
+ checkpoint_500000/target.decoder.layers_4.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
204
+ checkpoint_500000/target.decoder.layers_4.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
205
+ checkpoint_500000/target.decoder.layers_4.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
206
+ checkpoint_500000/target.decoder.layers_4.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
207
+ checkpoint_500000/target.decoder.layers_4.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
208
+ checkpoint_500000/target.decoder.layers_4.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
209
+ checkpoint_500000/target.decoder.layers_4.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
210
+ checkpoint_500000/target.decoder.layers_4.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
211
+ checkpoint_500000/target.decoder.layers_4.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
212
+ checkpoint_500000/target.decoder.layers_4.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
213
+ checkpoint_500000/target.decoder.layers_4.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
214
+ checkpoint_500000/target.decoder.layers_4.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
215
+ checkpoint_500000/target.decoder.layers_4.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
216
+ checkpoint_500000/target.decoder.layers_5.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
217
+ checkpoint_500000/target.decoder.layers_5.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
218
+ checkpoint_500000/target.decoder.layers_5.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
219
+ checkpoint_500000/target.decoder.layers_5.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
220
+ checkpoint_500000/target.decoder.layers_5.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
221
+ checkpoint_500000/target.decoder.layers_5.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
222
+ checkpoint_500000/target.decoder.layers_5.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
223
+ checkpoint_500000/target.decoder.layers_5.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
224
+ checkpoint_500000/target.decoder.layers_5.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
225
+ checkpoint_500000/target.decoder.layers_5.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
226
+ checkpoint_500000/target.decoder.layers_5.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
227
+ checkpoint_500000/target.decoder.layers_5.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
228
+ checkpoint_500000/target.decoder.layers_5.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
229
+ checkpoint_500000/target.decoder.layers_6.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
230
+ checkpoint_500000/target.decoder.layers_6.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
231
+ checkpoint_500000/target.decoder.layers_6.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
232
+ checkpoint_500000/target.decoder.layers_6.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
233
+ checkpoint_500000/target.decoder.layers_6.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
234
+ checkpoint_500000/target.decoder.layers_6.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
235
+ checkpoint_500000/target.decoder.layers_6.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
236
+ checkpoint_500000/target.decoder.layers_6.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
237
+ checkpoint_500000/target.decoder.layers_6.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
238
+ checkpoint_500000/target.decoder.layers_6.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
239
+ checkpoint_500000/target.decoder.layers_6.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
240
+ checkpoint_500000/target.decoder.layers_6.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
241
+ checkpoint_500000/target.decoder.layers_6.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
242
+ checkpoint_500000/target.decoder.layers_7.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
243
+ checkpoint_500000/target.decoder.layers_7.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
244
+ checkpoint_500000/target.decoder.layers_7.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
245
+ checkpoint_500000/target.decoder.layers_7.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
246
+ checkpoint_500000/target.decoder.layers_7.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
247
+ checkpoint_500000/target.decoder.layers_7.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
248
+ checkpoint_500000/target.decoder.layers_7.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
249
+ checkpoint_500000/target.decoder.layers_7.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
250
+ checkpoint_500000/target.decoder.layers_7.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
251
+ checkpoint_500000/target.decoder.layers_7.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
252
+ checkpoint_500000/target.decoder.layers_7.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
253
+ checkpoint_500000/target.decoder.layers_7.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
254
+ checkpoint_500000/target.decoder.layers_7.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
255
+ checkpoint_500000/target.decoder.layers_8.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
256
+ checkpoint_500000/target.decoder.layers_8.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
257
+ checkpoint_500000/target.decoder.layers_8.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
258
+ checkpoint_500000/target.decoder.layers_8.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
259
+ checkpoint_500000/target.decoder.layers_8.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
260
+ checkpoint_500000/target.decoder.layers_8.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
261
+ checkpoint_500000/target.decoder.layers_8.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
262
+ checkpoint_500000/target.decoder.layers_8.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
263
+ checkpoint_500000/target.decoder.layers_8.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
264
+ checkpoint_500000/target.decoder.layers_8.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
265
+ checkpoint_500000/target.decoder.layers_8.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
266
+ checkpoint_500000/target.decoder.layers_8.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
267
+ checkpoint_500000/target.decoder.layers_8.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
268
+ checkpoint_500000/target.decoder.layers_9.FiLMLayer_0.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
269
+ checkpoint_500000/target.decoder.layers_9.FiLMLayer_1.DenseGeneral_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
270
+ checkpoint_500000/target.decoder.layers_9.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
271
+ checkpoint_500000/target.decoder.layers_9.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
272
+ checkpoint_500000/target.decoder.layers_9.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
273
+ checkpoint_500000/target.decoder.layers_9.MultiHeadDotProductAttention_0.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
274
+ checkpoint_500000/target.decoder.layers_9.MultiHeadDotProductAttention_0.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
275
+ checkpoint_500000/target.decoder.layers_9.MultiHeadDotProductAttention_0.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
276
+ checkpoint_500000/target.decoder.layers_9.MultiHeadDotProductAttention_0.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
277
+ checkpoint_500000/target.decoder.layers_9.self_attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
278
+ checkpoint_500000/target.decoder.layers_9.self_attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
279
+ checkpoint_500000/target.decoder.layers_9.self_attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
280
+ checkpoint_500000/target.decoder.layers_9.self_attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
281
+ checkpoint_500000/target.decoder.spec_out_dense.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
282
+ checkpoint_500000/target.decoder.time_emb_dense0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
283
+ checkpoint_500000/target.decoder.time_emb_dense1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
284
+ checkpoint_500000/target.token_encoder.Embed_0.embedding/0.0 filter=lfs diff=lfs merge=lfs -text
285
+ checkpoint_500000/target.token_encoder.layers_0.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
286
+ checkpoint_500000/target.token_encoder.layers_0.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
287
+ checkpoint_500000/target.token_encoder.layers_0.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
288
+ checkpoint_500000/target.token_encoder.layers_0.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
289
+ checkpoint_500000/target.token_encoder.layers_0.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
290
+ checkpoint_500000/target.token_encoder.layers_0.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
291
+ checkpoint_500000/target.token_encoder.layers_0.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
292
+ checkpoint_500000/target.token_encoder.layers_1.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
293
+ checkpoint_500000/target.token_encoder.layers_1.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
294
+ checkpoint_500000/target.token_encoder.layers_1.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
295
+ checkpoint_500000/target.token_encoder.layers_1.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
296
+ checkpoint_500000/target.token_encoder.layers_1.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
297
+ checkpoint_500000/target.token_encoder.layers_1.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
298
+ checkpoint_500000/target.token_encoder.layers_1.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
299
+ checkpoint_500000/target.token_encoder.layers_10.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
300
+ checkpoint_500000/target.token_encoder.layers_10.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
301
+ checkpoint_500000/target.token_encoder.layers_10.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
302
+ checkpoint_500000/target.token_encoder.layers_10.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
303
+ checkpoint_500000/target.token_encoder.layers_10.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
304
+ checkpoint_500000/target.token_encoder.layers_10.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
305
+ checkpoint_500000/target.token_encoder.layers_10.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
306
+ checkpoint_500000/target.token_encoder.layers_11.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
307
+ checkpoint_500000/target.token_encoder.layers_11.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
308
+ checkpoint_500000/target.token_encoder.layers_11.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
309
+ checkpoint_500000/target.token_encoder.layers_11.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
310
+ checkpoint_500000/target.token_encoder.layers_11.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
311
+ checkpoint_500000/target.token_encoder.layers_11.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
312
+ checkpoint_500000/target.token_encoder.layers_11.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
313
+ checkpoint_500000/target.token_encoder.layers_2.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
314
+ checkpoint_500000/target.token_encoder.layers_2.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
315
+ checkpoint_500000/target.token_encoder.layers_2.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
316
+ checkpoint_500000/target.token_encoder.layers_2.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
317
+ checkpoint_500000/target.token_encoder.layers_2.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
318
+ checkpoint_500000/target.token_encoder.layers_2.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
319
+ checkpoint_500000/target.token_encoder.layers_2.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
320
+ checkpoint_500000/target.token_encoder.layers_3.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
321
+ checkpoint_500000/target.token_encoder.layers_3.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
322
+ checkpoint_500000/target.token_encoder.layers_3.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
323
+ checkpoint_500000/target.token_encoder.layers_3.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
324
+ checkpoint_500000/target.token_encoder.layers_3.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
325
+ checkpoint_500000/target.token_encoder.layers_3.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
326
+ checkpoint_500000/target.token_encoder.layers_3.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
327
+ checkpoint_500000/target.token_encoder.layers_4.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
328
+ checkpoint_500000/target.token_encoder.layers_4.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
329
+ checkpoint_500000/target.token_encoder.layers_4.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
330
+ checkpoint_500000/target.token_encoder.layers_4.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
331
+ checkpoint_500000/target.token_encoder.layers_4.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
332
+ checkpoint_500000/target.token_encoder.layers_4.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
333
+ checkpoint_500000/target.token_encoder.layers_4.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
334
+ checkpoint_500000/target.token_encoder.layers_5.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
335
+ checkpoint_500000/target.token_encoder.layers_5.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
336
+ checkpoint_500000/target.token_encoder.layers_5.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
337
+ checkpoint_500000/target.token_encoder.layers_5.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
338
+ checkpoint_500000/target.token_encoder.layers_5.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
339
+ checkpoint_500000/target.token_encoder.layers_5.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
340
+ checkpoint_500000/target.token_encoder.layers_5.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
341
+ checkpoint_500000/target.token_encoder.layers_6.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
342
+ checkpoint_500000/target.token_encoder.layers_6.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
343
+ checkpoint_500000/target.token_encoder.layers_6.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
344
+ checkpoint_500000/target.token_encoder.layers_6.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
345
+ checkpoint_500000/target.token_encoder.layers_6.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
346
+ checkpoint_500000/target.token_encoder.layers_6.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
347
+ checkpoint_500000/target.token_encoder.layers_6.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
348
+ checkpoint_500000/target.token_encoder.layers_7.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
349
+ checkpoint_500000/target.token_encoder.layers_7.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
350
+ checkpoint_500000/target.token_encoder.layers_7.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
351
+ checkpoint_500000/target.token_encoder.layers_7.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
352
+ checkpoint_500000/target.token_encoder.layers_7.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
353
+ checkpoint_500000/target.token_encoder.layers_7.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
354
+ checkpoint_500000/target.token_encoder.layers_7.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
355
+ checkpoint_500000/target.token_encoder.layers_8.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
356
+ checkpoint_500000/target.token_encoder.layers_8.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
357
+ checkpoint_500000/target.token_encoder.layers_8.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
358
+ checkpoint_500000/target.token_encoder.layers_8.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
359
+ checkpoint_500000/target.token_encoder.layers_8.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
360
+ checkpoint_500000/target.token_encoder.layers_8.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
361
+ checkpoint_500000/target.token_encoder.layers_8.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
362
+ checkpoint_500000/target.token_encoder.layers_9.attention.key.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
363
+ checkpoint_500000/target.token_encoder.layers_9.attention.out.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
364
+ checkpoint_500000/target.token_encoder.layers_9.attention.query.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
365
+ checkpoint_500000/target.token_encoder.layers_9.attention.value.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
366
+ checkpoint_500000/target.token_encoder.layers_9.mlp.wi_0.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
367
+ checkpoint_500000/target.token_encoder.layers_9.mlp.wi_1.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
368
+ checkpoint_500000/target.token_encoder.layers_9.mlp.wo.kernel/0.0 filter=lfs diff=lfs merge=lfs -text
369
+ checkpoint_500000/target.token_encoder.token_embedder.embedding/0.0 filter=lfs diff=lfs merge=lfs -text
checkpoint_500000/checkpoint ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb07f44d77a75f0778c1bac3f9cb736b973c7fcd5b663cc6303aa33fccb1212
3
+ size 3064194
checkpoint_500000/state.param_states.continuous_encoder.encoder_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.encoder_norm.scale.v/0 ADDED
Binary file (2.8 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_0.pre_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_0.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (2.85 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_0.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_0.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (2.83 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_1.pre_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_1.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (2.81 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_1.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_1.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (2.78 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_10.pre_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_10.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (2.77 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_10.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_10.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (2.67 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_11.pre_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_11.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (2.79 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_11.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_11.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (2.75 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_2.pre_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_2.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (2.78 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_2.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_2.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (2.74 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_3.pre_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_3.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (2.73 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_3.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_3.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (2.69 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_4.pre_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_4.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (2.76 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_4.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_4.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (2.71 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_5.pre_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_5.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (2.77 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_5.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_5.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (2.75 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_6.pre_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_6.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (2.71 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_6.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_6.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (2.69 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_7.pre_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_7.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (2.69 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_7.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_7.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (2.68 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_8.pre_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_8.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (2.69 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_8.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_8.pre_mlp_layer_norm.scale.v/0 ADDED
Binary file (2.67 kB). View file
 
checkpoint_500000/state.param_states.continuous_encoder.layers_9.pre_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chunks":[768],"compressor":{"id":"gzip","level":1},"dimension_separator":".","dtype":"<f4","fill_value":null,"filters":null,"order":"C","shape":[768],"zarr_format":2}
checkpoint_500000/state.param_states.continuous_encoder.layers_9.pre_attention_layer_norm.scale.v/0 ADDED
Binary file (2.74 kB). View file