Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +513 -0
- olmo_core/.metadata.json +1 -0
- olmo_core/config.json +361 -0
- olmo_core/model_and_optim/.metadata +3 -0
- olmo_core/model_and_optim/__0_0.distcp +3 -0
- olmo_core/model_and_optim/__0_1.distcp +3 -0
- olmo_core/model_and_optim/__0_10.distcp +3 -0
- olmo_core/model_and_optim/__0_11.distcp +3 -0
- olmo_core/model_and_optim/__0_12.distcp +3 -0
- olmo_core/model_and_optim/__0_13.distcp +3 -0
- olmo_core/model_and_optim/__0_14.distcp +3 -0
- olmo_core/model_and_optim/__0_15.distcp +3 -0
- olmo_core/model_and_optim/__0_2.distcp +3 -0
- olmo_core/model_and_optim/__0_3.distcp +3 -0
- olmo_core/model_and_optim/__0_4.distcp +3 -0
- olmo_core/model_and_optim/__0_5.distcp +3 -0
- olmo_core/model_and_optim/__0_6.distcp +3 -0
- olmo_core/model_and_optim/__0_7.distcp +3 -0
- olmo_core/model_and_optim/__0_8.distcp +3 -0
- olmo_core/model_and_optim/__0_9.distcp +3 -0
- olmo_core/model_and_optim/__10_0.distcp +3 -0
- olmo_core/model_and_optim/__10_1.distcp +3 -0
- olmo_core/model_and_optim/__10_10.distcp +3 -0
- olmo_core/model_and_optim/__10_11.distcp +3 -0
- olmo_core/model_and_optim/__10_12.distcp +3 -0
- olmo_core/model_and_optim/__10_13.distcp +3 -0
- olmo_core/model_and_optim/__10_14.distcp +3 -0
- olmo_core/model_and_optim/__10_15.distcp +3 -0
- olmo_core/model_and_optim/__10_2.distcp +3 -0
- olmo_core/model_and_optim/__10_3.distcp +3 -0
- olmo_core/model_and_optim/__10_4.distcp +3 -0
- olmo_core/model_and_optim/__10_5.distcp +3 -0
- olmo_core/model_and_optim/__10_6.distcp +3 -0
- olmo_core/model_and_optim/__10_7.distcp +3 -0
- olmo_core/model_and_optim/__10_8.distcp +3 -0
- olmo_core/model_and_optim/__10_9.distcp +3 -0
- olmo_core/model_and_optim/__11_0.distcp +3 -0
- olmo_core/model_and_optim/__11_1.distcp +3 -0
- olmo_core/model_and_optim/__11_10.distcp +3 -0
- olmo_core/model_and_optim/__11_11.distcp +3 -0
- olmo_core/model_and_optim/__11_12.distcp +3 -0
- olmo_core/model_and_optim/__11_13.distcp +3 -0
- olmo_core/model_and_optim/__11_14.distcp +3 -0
- olmo_core/model_and_optim/__11_15.distcp +3 -0
- olmo_core/model_and_optim/__11_2.distcp +3 -0
- olmo_core/model_and_optim/__11_3.distcp +3 -0
- olmo_core/model_and_optim/__11_4.distcp +3 -0
- olmo_core/model_and_optim/__11_5.distcp +3 -0
- olmo_core/model_and_optim/__11_6.distcp +3 -0
- olmo_core/model_and_optim/__11_7.distcp +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,516 @@ 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 |
+
olmo_core/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
olmo_core/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
olmo_core/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
olmo_core/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
olmo_core/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
olmo_core/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
olmo_core/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
olmo_core/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
olmo_core/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
olmo_core/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
olmo_core/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
olmo_core/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
olmo_core/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
olmo_core/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
olmo_core/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
olmo_core/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
olmo_core/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
olmo_core/model_and_optim/__10_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
olmo_core/model_and_optim/__10_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
olmo_core/model_and_optim/__10_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
olmo_core/model_and_optim/__10_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
olmo_core/model_and_optim/__10_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
olmo_core/model_and_optim/__10_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 59 |
+
olmo_core/model_and_optim/__10_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 60 |
+
olmo_core/model_and_optim/__10_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 61 |
+
olmo_core/model_and_optim/__10_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
olmo_core/model_and_optim/__10_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 63 |
+
olmo_core/model_and_optim/__10_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 64 |
+
olmo_core/model_and_optim/__10_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 65 |
+
olmo_core/model_and_optim/__10_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 66 |
+
olmo_core/model_and_optim/__10_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 67 |
+
olmo_core/model_and_optim/__10_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 68 |
+
olmo_core/model_and_optim/__10_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 69 |
+
olmo_core/model_and_optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 70 |
+
olmo_core/model_and_optim/__11_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 71 |
+
olmo_core/model_and_optim/__11_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 72 |
+
olmo_core/model_and_optim/__11_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 73 |
+
olmo_core/model_and_optim/__11_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 74 |
+
olmo_core/model_and_optim/__11_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 75 |
+
olmo_core/model_and_optim/__11_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 76 |
+
olmo_core/model_and_optim/__11_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 77 |
+
olmo_core/model_and_optim/__11_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 78 |
+
olmo_core/model_and_optim/__11_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 79 |
+
olmo_core/model_and_optim/__11_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 80 |
+
olmo_core/model_and_optim/__11_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 81 |
+
olmo_core/model_and_optim/__11_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 82 |
+
olmo_core/model_and_optim/__11_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 83 |
+
olmo_core/model_and_optim/__11_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 84 |
+
olmo_core/model_and_optim/__11_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 85 |
+
olmo_core/model_and_optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 86 |
+
olmo_core/model_and_optim/__12_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 87 |
+
olmo_core/model_and_optim/__12_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 88 |
+
olmo_core/model_and_optim/__12_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 89 |
+
olmo_core/model_and_optim/__12_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 90 |
+
olmo_core/model_and_optim/__12_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 91 |
+
olmo_core/model_and_optim/__12_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 92 |
+
olmo_core/model_and_optim/__12_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 93 |
+
olmo_core/model_and_optim/__12_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 94 |
+
olmo_core/model_and_optim/__12_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 95 |
+
olmo_core/model_and_optim/__12_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 96 |
+
olmo_core/model_and_optim/__12_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 97 |
+
olmo_core/model_and_optim/__12_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 98 |
+
olmo_core/model_and_optim/__12_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 99 |
+
olmo_core/model_and_optim/__12_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 100 |
+
olmo_core/model_and_optim/__12_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 101 |
+
olmo_core/model_and_optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 102 |
+
olmo_core/model_and_optim/__13_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 103 |
+
olmo_core/model_and_optim/__13_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 104 |
+
olmo_core/model_and_optim/__13_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 105 |
+
olmo_core/model_and_optim/__13_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 106 |
+
olmo_core/model_and_optim/__13_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 107 |
+
olmo_core/model_and_optim/__13_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 108 |
+
olmo_core/model_and_optim/__13_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 109 |
+
olmo_core/model_and_optim/__13_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 110 |
+
olmo_core/model_and_optim/__13_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 111 |
+
olmo_core/model_and_optim/__13_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 112 |
+
olmo_core/model_and_optim/__13_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 113 |
+
olmo_core/model_and_optim/__13_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 114 |
+
olmo_core/model_and_optim/__13_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 115 |
+
olmo_core/model_and_optim/__13_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 116 |
+
olmo_core/model_and_optim/__13_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 117 |
+
olmo_core/model_and_optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 118 |
+
olmo_core/model_and_optim/__14_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 119 |
+
olmo_core/model_and_optim/__14_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 120 |
+
olmo_core/model_and_optim/__14_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 121 |
+
olmo_core/model_and_optim/__14_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 122 |
+
olmo_core/model_and_optim/__14_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 123 |
+
olmo_core/model_and_optim/__14_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 124 |
+
olmo_core/model_and_optim/__14_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 125 |
+
olmo_core/model_and_optim/__14_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 126 |
+
olmo_core/model_and_optim/__14_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 127 |
+
olmo_core/model_and_optim/__14_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 128 |
+
olmo_core/model_and_optim/__14_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 129 |
+
olmo_core/model_and_optim/__14_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 130 |
+
olmo_core/model_and_optim/__14_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 131 |
+
olmo_core/model_and_optim/__14_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 132 |
+
olmo_core/model_and_optim/__14_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 133 |
+
olmo_core/model_and_optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 134 |
+
olmo_core/model_and_optim/__15_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 135 |
+
olmo_core/model_and_optim/__15_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 136 |
+
olmo_core/model_and_optim/__15_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 137 |
+
olmo_core/model_and_optim/__15_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 138 |
+
olmo_core/model_and_optim/__15_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 139 |
+
olmo_core/model_and_optim/__15_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 140 |
+
olmo_core/model_and_optim/__15_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 141 |
+
olmo_core/model_and_optim/__15_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 142 |
+
olmo_core/model_and_optim/__15_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 143 |
+
olmo_core/model_and_optim/__15_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 144 |
+
olmo_core/model_and_optim/__15_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 145 |
+
olmo_core/model_and_optim/__15_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 146 |
+
olmo_core/model_and_optim/__15_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 147 |
+
olmo_core/model_and_optim/__15_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 148 |
+
olmo_core/model_and_optim/__15_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 149 |
+
olmo_core/model_and_optim/__16_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 150 |
+
olmo_core/model_and_optim/__16_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 151 |
+
olmo_core/model_and_optim/__16_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 152 |
+
olmo_core/model_and_optim/__16_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 153 |
+
olmo_core/model_and_optim/__16_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 154 |
+
olmo_core/model_and_optim/__16_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 155 |
+
olmo_core/model_and_optim/__16_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 156 |
+
olmo_core/model_and_optim/__16_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 157 |
+
olmo_core/model_and_optim/__16_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 158 |
+
olmo_core/model_and_optim/__16_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 159 |
+
olmo_core/model_and_optim/__16_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 160 |
+
olmo_core/model_and_optim/__16_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 161 |
+
olmo_core/model_and_optim/__16_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 162 |
+
olmo_core/model_and_optim/__16_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 163 |
+
olmo_core/model_and_optim/__16_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 164 |
+
olmo_core/model_and_optim/__16_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 165 |
+
olmo_core/model_and_optim/__17_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 166 |
+
olmo_core/model_and_optim/__17_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 167 |
+
olmo_core/model_and_optim/__17_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 168 |
+
olmo_core/model_and_optim/__17_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 169 |
+
olmo_core/model_and_optim/__17_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 170 |
+
olmo_core/model_and_optim/__17_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 171 |
+
olmo_core/model_and_optim/__17_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 172 |
+
olmo_core/model_and_optim/__17_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 173 |
+
olmo_core/model_and_optim/__17_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 174 |
+
olmo_core/model_and_optim/__17_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 175 |
+
olmo_core/model_and_optim/__17_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 176 |
+
olmo_core/model_and_optim/__17_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 177 |
+
olmo_core/model_and_optim/__17_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 178 |
+
olmo_core/model_and_optim/__17_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 179 |
+
olmo_core/model_and_optim/__17_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 180 |
+
olmo_core/model_and_optim/__17_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 181 |
+
olmo_core/model_and_optim/__18_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 182 |
+
olmo_core/model_and_optim/__18_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 183 |
+
olmo_core/model_and_optim/__18_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 184 |
+
olmo_core/model_and_optim/__18_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 185 |
+
olmo_core/model_and_optim/__18_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 186 |
+
olmo_core/model_and_optim/__18_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 187 |
+
olmo_core/model_and_optim/__18_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 188 |
+
olmo_core/model_and_optim/__18_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 189 |
+
olmo_core/model_and_optim/__18_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 190 |
+
olmo_core/model_and_optim/__18_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 191 |
+
olmo_core/model_and_optim/__18_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 192 |
+
olmo_core/model_and_optim/__18_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 193 |
+
olmo_core/model_and_optim/__18_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 194 |
+
olmo_core/model_and_optim/__18_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 195 |
+
olmo_core/model_and_optim/__18_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 196 |
+
olmo_core/model_and_optim/__18_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 197 |
+
olmo_core/model_and_optim/__19_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 198 |
+
olmo_core/model_and_optim/__19_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 199 |
+
olmo_core/model_and_optim/__19_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 200 |
+
olmo_core/model_and_optim/__19_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 201 |
+
olmo_core/model_and_optim/__19_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 202 |
+
olmo_core/model_and_optim/__19_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 203 |
+
olmo_core/model_and_optim/__19_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 204 |
+
olmo_core/model_and_optim/__19_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 205 |
+
olmo_core/model_and_optim/__19_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 206 |
+
olmo_core/model_and_optim/__19_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 207 |
+
olmo_core/model_and_optim/__19_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 208 |
+
olmo_core/model_and_optim/__19_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 209 |
+
olmo_core/model_and_optim/__19_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 210 |
+
olmo_core/model_and_optim/__19_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 211 |
+
olmo_core/model_and_optim/__19_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 212 |
+
olmo_core/model_and_optim/__19_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 213 |
+
olmo_core/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 214 |
+
olmo_core/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 215 |
+
olmo_core/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 216 |
+
olmo_core/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 217 |
+
olmo_core/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 218 |
+
olmo_core/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 219 |
+
olmo_core/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 220 |
+
olmo_core/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 221 |
+
olmo_core/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 222 |
+
olmo_core/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 223 |
+
olmo_core/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 224 |
+
olmo_core/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 225 |
+
olmo_core/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 226 |
+
olmo_core/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 227 |
+
olmo_core/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 228 |
+
olmo_core/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 229 |
+
olmo_core/model_and_optim/__20_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 230 |
+
olmo_core/model_and_optim/__20_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 231 |
+
olmo_core/model_and_optim/__20_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 232 |
+
olmo_core/model_and_optim/__20_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 233 |
+
olmo_core/model_and_optim/__20_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 234 |
+
olmo_core/model_and_optim/__20_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 235 |
+
olmo_core/model_and_optim/__20_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 236 |
+
olmo_core/model_and_optim/__20_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 237 |
+
olmo_core/model_and_optim/__20_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 238 |
+
olmo_core/model_and_optim/__20_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 239 |
+
olmo_core/model_and_optim/__20_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 240 |
+
olmo_core/model_and_optim/__20_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 241 |
+
olmo_core/model_and_optim/__20_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 242 |
+
olmo_core/model_and_optim/__20_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 243 |
+
olmo_core/model_and_optim/__20_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 244 |
+
olmo_core/model_and_optim/__20_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 245 |
+
olmo_core/model_and_optim/__21_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 246 |
+
olmo_core/model_and_optim/__21_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 247 |
+
olmo_core/model_and_optim/__21_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 248 |
+
olmo_core/model_and_optim/__21_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 249 |
+
olmo_core/model_and_optim/__21_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 250 |
+
olmo_core/model_and_optim/__21_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 251 |
+
olmo_core/model_and_optim/__21_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 252 |
+
olmo_core/model_and_optim/__21_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 253 |
+
olmo_core/model_and_optim/__21_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 254 |
+
olmo_core/model_and_optim/__21_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 255 |
+
olmo_core/model_and_optim/__21_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 256 |
+
olmo_core/model_and_optim/__21_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 257 |
+
olmo_core/model_and_optim/__21_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 258 |
+
olmo_core/model_and_optim/__21_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 259 |
+
olmo_core/model_and_optim/__21_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 260 |
+
olmo_core/model_and_optim/__21_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 261 |
+
olmo_core/model_and_optim/__22_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 262 |
+
olmo_core/model_and_optim/__22_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 263 |
+
olmo_core/model_and_optim/__22_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 264 |
+
olmo_core/model_and_optim/__22_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 265 |
+
olmo_core/model_and_optim/__22_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 266 |
+
olmo_core/model_and_optim/__22_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 267 |
+
olmo_core/model_and_optim/__22_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 268 |
+
olmo_core/model_and_optim/__22_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 269 |
+
olmo_core/model_and_optim/__22_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 270 |
+
olmo_core/model_and_optim/__22_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 271 |
+
olmo_core/model_and_optim/__22_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 272 |
+
olmo_core/model_and_optim/__22_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 273 |
+
olmo_core/model_and_optim/__22_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 274 |
+
olmo_core/model_and_optim/__22_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 275 |
+
olmo_core/model_and_optim/__22_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 276 |
+
olmo_core/model_and_optim/__22_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 277 |
+
olmo_core/model_and_optim/__23_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 278 |
+
olmo_core/model_and_optim/__23_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 279 |
+
olmo_core/model_and_optim/__23_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 280 |
+
olmo_core/model_and_optim/__23_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 281 |
+
olmo_core/model_and_optim/__23_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 282 |
+
olmo_core/model_and_optim/__23_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 283 |
+
olmo_core/model_and_optim/__23_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 284 |
+
olmo_core/model_and_optim/__23_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 285 |
+
olmo_core/model_and_optim/__23_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 286 |
+
olmo_core/model_and_optim/__23_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 287 |
+
olmo_core/model_and_optim/__23_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 288 |
+
olmo_core/model_and_optim/__23_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 289 |
+
olmo_core/model_and_optim/__23_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 290 |
+
olmo_core/model_and_optim/__23_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 291 |
+
olmo_core/model_and_optim/__23_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 292 |
+
olmo_core/model_and_optim/__23_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 293 |
+
olmo_core/model_and_optim/__24_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 294 |
+
olmo_core/model_and_optim/__24_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 295 |
+
olmo_core/model_and_optim/__24_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 296 |
+
olmo_core/model_and_optim/__24_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 297 |
+
olmo_core/model_and_optim/__24_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 298 |
+
olmo_core/model_and_optim/__24_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 299 |
+
olmo_core/model_and_optim/__24_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 300 |
+
olmo_core/model_and_optim/__24_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 301 |
+
olmo_core/model_and_optim/__24_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 302 |
+
olmo_core/model_and_optim/__24_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 303 |
+
olmo_core/model_and_optim/__24_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 304 |
+
olmo_core/model_and_optim/__24_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 305 |
+
olmo_core/model_and_optim/__24_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 306 |
+
olmo_core/model_and_optim/__24_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 307 |
+
olmo_core/model_and_optim/__24_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 308 |
+
olmo_core/model_and_optim/__24_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 309 |
+
olmo_core/model_and_optim/__25_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 310 |
+
olmo_core/model_and_optim/__25_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 311 |
+
olmo_core/model_and_optim/__25_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 312 |
+
olmo_core/model_and_optim/__25_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 313 |
+
olmo_core/model_and_optim/__25_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 314 |
+
olmo_core/model_and_optim/__25_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 315 |
+
olmo_core/model_and_optim/__25_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 316 |
+
olmo_core/model_and_optim/__25_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 317 |
+
olmo_core/model_and_optim/__25_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 318 |
+
olmo_core/model_and_optim/__25_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 319 |
+
olmo_core/model_and_optim/__25_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 320 |
+
olmo_core/model_and_optim/__25_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 321 |
+
olmo_core/model_and_optim/__25_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 322 |
+
olmo_core/model_and_optim/__25_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 323 |
+
olmo_core/model_and_optim/__25_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 324 |
+
olmo_core/model_and_optim/__25_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 325 |
+
olmo_core/model_and_optim/__26_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 326 |
+
olmo_core/model_and_optim/__26_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 327 |
+
olmo_core/model_and_optim/__26_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 328 |
+
olmo_core/model_and_optim/__26_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 329 |
+
olmo_core/model_and_optim/__26_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 330 |
+
olmo_core/model_and_optim/__26_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 331 |
+
olmo_core/model_and_optim/__26_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 332 |
+
olmo_core/model_and_optim/__26_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 333 |
+
olmo_core/model_and_optim/__26_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 334 |
+
olmo_core/model_and_optim/__26_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 335 |
+
olmo_core/model_and_optim/__26_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 336 |
+
olmo_core/model_and_optim/__26_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 337 |
+
olmo_core/model_and_optim/__26_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 338 |
+
olmo_core/model_and_optim/__26_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 339 |
+
olmo_core/model_and_optim/__26_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 340 |
+
olmo_core/model_and_optim/__26_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 341 |
+
olmo_core/model_and_optim/__27_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 342 |
+
olmo_core/model_and_optim/__27_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 343 |
+
olmo_core/model_and_optim/__27_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 344 |
+
olmo_core/model_and_optim/__27_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 345 |
+
olmo_core/model_and_optim/__27_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 346 |
+
olmo_core/model_and_optim/__27_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 347 |
+
olmo_core/model_and_optim/__27_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 348 |
+
olmo_core/model_and_optim/__27_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 349 |
+
olmo_core/model_and_optim/__27_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 350 |
+
olmo_core/model_and_optim/__27_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 351 |
+
olmo_core/model_and_optim/__27_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 352 |
+
olmo_core/model_and_optim/__27_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 353 |
+
olmo_core/model_and_optim/__27_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 354 |
+
olmo_core/model_and_optim/__27_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 355 |
+
olmo_core/model_and_optim/__27_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 356 |
+
olmo_core/model_and_optim/__27_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 357 |
+
olmo_core/model_and_optim/__28_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 358 |
+
olmo_core/model_and_optim/__28_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 359 |
+
olmo_core/model_and_optim/__28_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 360 |
+
olmo_core/model_and_optim/__28_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 361 |
+
olmo_core/model_and_optim/__28_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 362 |
+
olmo_core/model_and_optim/__28_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 363 |
+
olmo_core/model_and_optim/__28_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 364 |
+
olmo_core/model_and_optim/__28_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 365 |
+
olmo_core/model_and_optim/__28_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 366 |
+
olmo_core/model_and_optim/__28_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 367 |
+
olmo_core/model_and_optim/__28_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 368 |
+
olmo_core/model_and_optim/__28_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 369 |
+
olmo_core/model_and_optim/__28_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 370 |
+
olmo_core/model_and_optim/__28_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 371 |
+
olmo_core/model_and_optim/__28_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 372 |
+
olmo_core/model_and_optim/__28_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 373 |
+
olmo_core/model_and_optim/__29_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 374 |
+
olmo_core/model_and_optim/__29_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 375 |
+
olmo_core/model_and_optim/__29_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 376 |
+
olmo_core/model_and_optim/__29_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 377 |
+
olmo_core/model_and_optim/__29_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 378 |
+
olmo_core/model_and_optim/__29_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 379 |
+
olmo_core/model_and_optim/__29_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 380 |
+
olmo_core/model_and_optim/__29_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 381 |
+
olmo_core/model_and_optim/__29_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 382 |
+
olmo_core/model_and_optim/__29_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 383 |
+
olmo_core/model_and_optim/__29_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 384 |
+
olmo_core/model_and_optim/__29_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 385 |
+
olmo_core/model_and_optim/__29_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 386 |
+
olmo_core/model_and_optim/__29_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 387 |
+
olmo_core/model_and_optim/__29_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 388 |
+
olmo_core/model_and_optim/__29_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 389 |
+
olmo_core/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 390 |
+
olmo_core/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 391 |
+
olmo_core/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 392 |
+
olmo_core/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 393 |
+
olmo_core/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 394 |
+
olmo_core/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 395 |
+
olmo_core/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 396 |
+
olmo_core/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 397 |
+
olmo_core/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 398 |
+
olmo_core/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 399 |
+
olmo_core/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 400 |
+
olmo_core/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 401 |
+
olmo_core/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 402 |
+
olmo_core/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 403 |
+
olmo_core/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 404 |
+
olmo_core/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 405 |
+
olmo_core/model_and_optim/__30_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 406 |
+
olmo_core/model_and_optim/__30_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 407 |
+
olmo_core/model_and_optim/__30_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 408 |
+
olmo_core/model_and_optim/__30_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 409 |
+
olmo_core/model_and_optim/__30_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 410 |
+
olmo_core/model_and_optim/__30_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 411 |
+
olmo_core/model_and_optim/__30_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 412 |
+
olmo_core/model_and_optim/__30_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 413 |
+
olmo_core/model_and_optim/__30_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 414 |
+
olmo_core/model_and_optim/__30_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 415 |
+
olmo_core/model_and_optim/__30_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 416 |
+
olmo_core/model_and_optim/__30_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 417 |
+
olmo_core/model_and_optim/__30_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 418 |
+
olmo_core/model_and_optim/__30_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 419 |
+
olmo_core/model_and_optim/__30_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 420 |
+
olmo_core/model_and_optim/__30_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 421 |
+
olmo_core/model_and_optim/__31_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 422 |
+
olmo_core/model_and_optim/__31_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 423 |
+
olmo_core/model_and_optim/__31_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 424 |
+
olmo_core/model_and_optim/__31_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 425 |
+
olmo_core/model_and_optim/__31_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 426 |
+
olmo_core/model_and_optim/__31_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 427 |
+
olmo_core/model_and_optim/__31_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 428 |
+
olmo_core/model_and_optim/__31_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 429 |
+
olmo_core/model_and_optim/__31_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 430 |
+
olmo_core/model_and_optim/__31_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 431 |
+
olmo_core/model_and_optim/__31_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 432 |
+
olmo_core/model_and_optim/__31_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 433 |
+
olmo_core/model_and_optim/__31_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 434 |
+
olmo_core/model_and_optim/__31_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 435 |
+
olmo_core/model_and_optim/__31_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 436 |
+
olmo_core/model_and_optim/__31_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 437 |
+
olmo_core/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 438 |
+
olmo_core/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 439 |
+
olmo_core/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 440 |
+
olmo_core/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 441 |
+
olmo_core/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 442 |
+
olmo_core/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 443 |
+
olmo_core/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 444 |
+
olmo_core/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 445 |
+
olmo_core/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 446 |
+
olmo_core/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 447 |
+
olmo_core/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 448 |
+
olmo_core/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 449 |
+
olmo_core/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 450 |
+
olmo_core/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 451 |
+
olmo_core/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 452 |
+
olmo_core/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 453 |
+
olmo_core/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 454 |
+
olmo_core/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 455 |
+
olmo_core/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 456 |
+
olmo_core/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 457 |
+
olmo_core/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 458 |
+
olmo_core/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 459 |
+
olmo_core/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 460 |
+
olmo_core/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 461 |
+
olmo_core/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 462 |
+
olmo_core/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 463 |
+
olmo_core/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 464 |
+
olmo_core/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 465 |
+
olmo_core/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 466 |
+
olmo_core/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 467 |
+
olmo_core/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 468 |
+
olmo_core/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 469 |
+
olmo_core/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 470 |
+
olmo_core/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 471 |
+
olmo_core/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 472 |
+
olmo_core/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 473 |
+
olmo_core/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 474 |
+
olmo_core/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 475 |
+
olmo_core/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 476 |
+
olmo_core/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 477 |
+
olmo_core/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 478 |
+
olmo_core/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 479 |
+
olmo_core/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 480 |
+
olmo_core/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 481 |
+
olmo_core/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 482 |
+
olmo_core/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 483 |
+
olmo_core/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 484 |
+
olmo_core/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 485 |
+
olmo_core/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 486 |
+
olmo_core/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 487 |
+
olmo_core/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 488 |
+
olmo_core/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 489 |
+
olmo_core/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 490 |
+
olmo_core/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 491 |
+
olmo_core/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 492 |
+
olmo_core/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 493 |
+
olmo_core/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 494 |
+
olmo_core/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 495 |
+
olmo_core/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 496 |
+
olmo_core/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 497 |
+
olmo_core/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 498 |
+
olmo_core/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 499 |
+
olmo_core/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 500 |
+
olmo_core/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 501 |
+
olmo_core/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 502 |
+
olmo_core/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 503 |
+
olmo_core/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 504 |
+
olmo_core/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 505 |
+
olmo_core/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 506 |
+
olmo_core/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 507 |
+
olmo_core/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 508 |
+
olmo_core/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 509 |
+
olmo_core/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 510 |
+
olmo_core/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 511 |
+
olmo_core/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 512 |
+
olmo_core/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 513 |
+
olmo_core/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 514 |
+
olmo_core/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 515 |
+
olmo_core/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 516 |
+
olmo_core/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 517 |
+
olmo_core/model_and_optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 518 |
+
olmo_core/model_and_optim/__8_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 519 |
+
olmo_core/model_and_optim/__8_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 520 |
+
olmo_core/model_and_optim/__8_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 521 |
+
olmo_core/model_and_optim/__8_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 522 |
+
olmo_core/model_and_optim/__8_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 523 |
+
olmo_core/model_and_optim/__8_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 524 |
+
olmo_core/model_and_optim/__8_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 525 |
+
olmo_core/model_and_optim/__8_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 526 |
+
olmo_core/model_and_optim/__8_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 527 |
+
olmo_core/model_and_optim/__8_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 528 |
+
olmo_core/model_and_optim/__8_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 529 |
+
olmo_core/model_and_optim/__8_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 530 |
+
olmo_core/model_and_optim/__8_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 531 |
+
olmo_core/model_and_optim/__8_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 532 |
+
olmo_core/model_and_optim/__8_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 533 |
+
olmo_core/model_and_optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 534 |
+
olmo_core/model_and_optim/__9_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 535 |
+
olmo_core/model_and_optim/__9_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 536 |
+
olmo_core/model_and_optim/__9_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 537 |
+
olmo_core/model_and_optim/__9_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 538 |
+
olmo_core/model_and_optim/__9_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 539 |
+
olmo_core/model_and_optim/__9_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 540 |
+
olmo_core/model_and_optim/__9_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 541 |
+
olmo_core/model_and_optim/__9_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 542 |
+
olmo_core/model_and_optim/__9_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 543 |
+
olmo_core/model_and_optim/__9_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 544 |
+
olmo_core/model_and_optim/__9_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 545 |
+
olmo_core/model_and_optim/__9_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 546 |
+
olmo_core/model_and_optim/__9_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 547 |
+
olmo_core/model_and_optim/__9_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 548 |
+
olmo_core/model_and_optim/__9_9.distcp filter=lfs diff=lfs merge=lfs -text
|
olmo_core/.metadata.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"version": "2.3.0"}
|
olmo_core/config.json
ADDED
|
@@ -0,0 +1,361 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": {
|
| 3 |
+
"d_model": 4096,
|
| 4 |
+
"vocab_size": 640,
|
| 5 |
+
"n_layers": 32,
|
| 6 |
+
"block": {
|
| 7 |
+
"attention": {
|
| 8 |
+
"name": "default",
|
| 9 |
+
"n_heads": 32,
|
| 10 |
+
"bias": false,
|
| 11 |
+
"rope": {
|
| 12 |
+
"name": "default",
|
| 13 |
+
"theta": 500000,
|
| 14 |
+
"full_precision": true,
|
| 15 |
+
"_CLASS_": "olmo_core.nn.rope.RoPEConfig"
|
| 16 |
+
},
|
| 17 |
+
"qk_norm": {
|
| 18 |
+
"name": "rms",
|
| 19 |
+
"eps": 1e-06,
|
| 20 |
+
"bias": false,
|
| 21 |
+
"dtype": "float32",
|
| 22 |
+
"_CLASS_": "olmo_core.nn.layer_norm.LayerNormConfig"
|
| 23 |
+
},
|
| 24 |
+
"use_flash": true,
|
| 25 |
+
"backend": "flash_2",
|
| 26 |
+
"dtype": "float32",
|
| 27 |
+
"sliding_window": {
|
| 28 |
+
"pattern": [
|
| 29 |
+
4096,
|
| 30 |
+
4096,
|
| 31 |
+
4096,
|
| 32 |
+
-1
|
| 33 |
+
],
|
| 34 |
+
"force_full_attention_on_first_layer": false,
|
| 35 |
+
"force_full_attention_on_last_layer": true,
|
| 36 |
+
"_CLASS_": "olmo_core.nn.attention.SlidingWindowAttentionConfig"
|
| 37 |
+
},
|
| 38 |
+
"_CLASS_": "olmo_core.nn.attention.AttentionConfig"
|
| 39 |
+
},
|
| 40 |
+
"layer_norm": {
|
| 41 |
+
"name": "rms",
|
| 42 |
+
"eps": 1e-06,
|
| 43 |
+
"bias": false,
|
| 44 |
+
"dtype": "float32",
|
| 45 |
+
"_CLASS_": "olmo_core.nn.layer_norm.LayerNormConfig"
|
| 46 |
+
},
|
| 47 |
+
"feed_forward": {
|
| 48 |
+
"hidden_size": 11008,
|
| 49 |
+
"name": "default",
|
| 50 |
+
"bias": false,
|
| 51 |
+
"dtype": "float32",
|
| 52 |
+
"act_name": "silu",
|
| 53 |
+
"_CLASS_": "olmo_core.nn.feed_forward.FeedForwardConfig"
|
| 54 |
+
},
|
| 55 |
+
"name": "reordered_norm",
|
| 56 |
+
"_CLASS_": "olmo_core.nn.transformer.config.TransformerBlockConfig"
|
| 57 |
+
},
|
| 58 |
+
"lm_head": {
|
| 59 |
+
"name": "default",
|
| 60 |
+
"layer_norm": {
|
| 61 |
+
"name": "rms",
|
| 62 |
+
"eps": 1e-06,
|
| 63 |
+
"bias": false,
|
| 64 |
+
"dtype": "float32",
|
| 65 |
+
"_CLASS_": "olmo_core.nn.layer_norm.LayerNormConfig"
|
| 66 |
+
},
|
| 67 |
+
"bias": false,
|
| 68 |
+
"dtype": "float32",
|
| 69 |
+
"loss_implementation": "default",
|
| 70 |
+
"_CLASS_": "olmo_core.nn.lm_head.LMHeadConfig"
|
| 71 |
+
},
|
| 72 |
+
"name": "bolmo_distill",
|
| 73 |
+
"dtype": "float32",
|
| 74 |
+
"init_method": "normal",
|
| 75 |
+
"init_seed": 0,
|
| 76 |
+
"init_std": 0.02,
|
| 77 |
+
"freeze_params": [
|
| 78 |
+
"boundary_predictor.*",
|
| 79 |
+
"teacher_embeddings.*"
|
| 80 |
+
],
|
| 81 |
+
"local_encoder": {
|
| 82 |
+
"sliding_window_size": 0,
|
| 83 |
+
"d_model": 4096,
|
| 84 |
+
"n_layers": 1,
|
| 85 |
+
"block_config": {
|
| 86 |
+
"attention": {
|
| 87 |
+
"name": "default",
|
| 88 |
+
"n_heads": 16,
|
| 89 |
+
"dtype": "float32",
|
| 90 |
+
"_CLASS_": "olmo_core.nn.attention.AttentionConfig"
|
| 91 |
+
},
|
| 92 |
+
"layer_norm": {
|
| 93 |
+
"name": "rms",
|
| 94 |
+
"eps": 1e-06,
|
| 95 |
+
"bias": false,
|
| 96 |
+
"dtype": "float32",
|
| 97 |
+
"_CLASS_": "olmo_core.nn.layer_norm.LayerNormConfig"
|
| 98 |
+
},
|
| 99 |
+
"feed_forward": {
|
| 100 |
+
"hidden_size": 5504,
|
| 101 |
+
"name": "default",
|
| 102 |
+
"bias": false,
|
| 103 |
+
"dtype": "float32",
|
| 104 |
+
"act_name": "silu",
|
| 105 |
+
"_CLASS_": "olmo_core.nn.feed_forward.FeedForwardConfig"
|
| 106 |
+
},
|
| 107 |
+
"xlstm": {
|
| 108 |
+
"num_heads": 16,
|
| 109 |
+
"dtype": "float32",
|
| 110 |
+
"_CLASS_": "olmo_core.nn.xlstm.XLSTMConfig"
|
| 111 |
+
},
|
| 112 |
+
"name": "xlstm",
|
| 113 |
+
"_CLASS_": "olmo_core.nn.transformer.config.TransformerBlockConfig"
|
| 114 |
+
},
|
| 115 |
+
"cross_attn_n_heads": 0,
|
| 116 |
+
"cross_attn_do_project": true,
|
| 117 |
+
"cross_attn_init_pooling": "amax",
|
| 118 |
+
"pooling": "hnet",
|
| 119 |
+
"add_hash_embeddings": false,
|
| 120 |
+
"add_expanded_embeddings": true,
|
| 121 |
+
"hash_byte_group_size": [
|
| 122 |
+
3,
|
| 123 |
+
4,
|
| 124 |
+
5,
|
| 125 |
+
6,
|
| 126 |
+
7,
|
| 127 |
+
8
|
| 128 |
+
],
|
| 129 |
+
"hash_byte_group_vocab": [
|
| 130 |
+
1536,
|
| 131 |
+
3072,
|
| 132 |
+
6144,
|
| 133 |
+
12288,
|
| 134 |
+
24576,
|
| 135 |
+
49152
|
| 136 |
+
],
|
| 137 |
+
"hash_byte_group_nb_functions": 1,
|
| 138 |
+
"add_norm_after_last_block": true,
|
| 139 |
+
"add_norm_after_pool": false,
|
| 140 |
+
"add_out_projection": true,
|
| 141 |
+
"boundary_predictor": "hnet",
|
| 142 |
+
"boundary_predictor_lookahead": 1,
|
| 143 |
+
"represent_bytes_with_embeddings": false,
|
| 144 |
+
"represent_bytes_with_last_mixed_out": false,
|
| 145 |
+
"blt_compat": false,
|
| 146 |
+
"dtype": "float32",
|
| 147 |
+
"_CLASS_": "olmo_core.nn.bolmo.config.LocalEncoderConfig"
|
| 148 |
+
},
|
| 149 |
+
"local_decoder": {
|
| 150 |
+
"sliding_window_size": 0,
|
| 151 |
+
"d_model": 4096,
|
| 152 |
+
"n_layers": 4,
|
| 153 |
+
"cross_attn_n_heads": 0,
|
| 154 |
+
"block_config": {
|
| 155 |
+
"attention": {
|
| 156 |
+
"name": "default",
|
| 157 |
+
"n_heads": 16,
|
| 158 |
+
"dtype": "float32",
|
| 159 |
+
"_CLASS_": "olmo_core.nn.attention.AttentionConfig"
|
| 160 |
+
},
|
| 161 |
+
"layer_norm": {
|
| 162 |
+
"name": "rms",
|
| 163 |
+
"eps": 1e-06,
|
| 164 |
+
"bias": false,
|
| 165 |
+
"dtype": "float32",
|
| 166 |
+
"_CLASS_": "olmo_core.nn.layer_norm.LayerNormConfig"
|
| 167 |
+
},
|
| 168 |
+
"feed_forward": {
|
| 169 |
+
"hidden_size": 5504,
|
| 170 |
+
"name": "default",
|
| 171 |
+
"bias": false,
|
| 172 |
+
"dtype": "float32",
|
| 173 |
+
"act_name": "silu",
|
| 174 |
+
"_CLASS_": "olmo_core.nn.feed_forward.FeedForwardConfig"
|
| 175 |
+
},
|
| 176 |
+
"xlstm": {
|
| 177 |
+
"num_heads": 16,
|
| 178 |
+
"dtype": "float32",
|
| 179 |
+
"_CLASS_": "olmo_core.nn.xlstm.XLSTMConfig"
|
| 180 |
+
},
|
| 181 |
+
"name": "xlstm",
|
| 182 |
+
"_CLASS_": "olmo_core.nn.transformer.config.TransformerBlockConfig"
|
| 183 |
+
},
|
| 184 |
+
"depooling": "hnet",
|
| 185 |
+
"add_norm_before_first_block": true,
|
| 186 |
+
"add_norm_onto_residual": false,
|
| 187 |
+
"add_in_projection": true,
|
| 188 |
+
"add_projected_patch_residuals": false,
|
| 189 |
+
"hnet_smooth": false,
|
| 190 |
+
"hnet_smooth_ste": false,
|
| 191 |
+
"hnet_modulate": false,
|
| 192 |
+
"blt_compat": false,
|
| 193 |
+
"fuse_boundaries": true,
|
| 194 |
+
"no_boundaries": false,
|
| 195 |
+
"dtype": "float32",
|
| 196 |
+
"_CLASS_": "olmo_core.nn.bolmo.config.LocalDecoderConfig"
|
| 197 |
+
},
|
| 198 |
+
"share_blocks_between_teacher_and_student": false,
|
| 199 |
+
"_CLASS_": "olmo_core.nn.transformer.config.TransformerConfig"
|
| 200 |
+
},
|
| 201 |
+
"dataset": {
|
| 202 |
+
"tokenizer": {
|
| 203 |
+
"vocab_size": 520,
|
| 204 |
+
"eos_token_id": 1,
|
| 205 |
+
"pad_token_id": 0,
|
| 206 |
+
"bos_token_id": 1,
|
| 207 |
+
"special_tokens": [
|
| 208 |
+
"<pad>",
|
| 209 |
+
"<bos>",
|
| 210 |
+
"<eos>",
|
| 211 |
+
"<bpe_token_end>"
|
| 212 |
+
],
|
| 213 |
+
"special_tokens_first": true,
|
| 214 |
+
"original_identifier": "allenai/dolma2-tokenizer",
|
| 215 |
+
"bpe_token_end_id": 3,
|
| 216 |
+
"_CLASS_": "olmo_core.data.tokenizer.ByteTokenizerConfig"
|
| 217 |
+
},
|
| 218 |
+
"paths": [],
|
| 219 |
+
"expand_glob": false,
|
| 220 |
+
"include_instance_metadata": true,
|
| 221 |
+
"work_dir": "",
|
| 222 |
+
"ignore_fingerprint_mismatch": false,
|
| 223 |
+
"sequence_length": 4096,
|
| 224 |
+
"generate_doc_lengths": false,
|
| 225 |
+
"byte_sequence_length": 24576,
|
| 226 |
+
"_CLASS_": "olmo_core.data.numpy_dataset.NumpyByteFSLDatasetConfig"
|
| 227 |
+
},
|
| 228 |
+
"data_loader": {
|
| 229 |
+
"global_batch_size": 1572864,
|
| 230 |
+
"seed": 1234,
|
| 231 |
+
"num_workers": 24,
|
| 232 |
+
"ignore_fingerprint_mismatch": false,
|
| 233 |
+
"_CLASS_": "olmo_core.data.data_loader.NumpyDataLoaderConfig"
|
| 234 |
+
},
|
| 235 |
+
"train_module": {
|
| 236 |
+
"rank_microbatch_size": 49152,
|
| 237 |
+
"max_sequence_length": 24576,
|
| 238 |
+
"optim": {
|
| 239 |
+
"group_overrides": [
|
| 240 |
+
{
|
| 241 |
+
"params": [
|
| 242 |
+
"local_encoder.embedding.weight",
|
| 243 |
+
"local_encoder.expanded_embeddings.weight"
|
| 244 |
+
],
|
| 245 |
+
"opts": {
|
| 246 |
+
"weight_decay": 0.0
|
| 247 |
+
},
|
| 248 |
+
"_CLASS_": "olmo_core.optim.config.OptimGroupOverride"
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"params": [
|
| 252 |
+
"blocks.*"
|
| 253 |
+
],
|
| 254 |
+
"opts": {
|
| 255 |
+
"lr": 1.83e-05
|
| 256 |
+
},
|
| 257 |
+
"_CLASS_": "olmo_core.optim.config.OptimGroupOverride"
|
| 258 |
+
}
|
| 259 |
+
],
|
| 260 |
+
"compile": false,
|
| 261 |
+
"fixed_fields": [
|
| 262 |
+
"initial_lr"
|
| 263 |
+
],
|
| 264 |
+
"lr": 3.66e-05,
|
| 265 |
+
"betas": [
|
| 266 |
+
0.9,
|
| 267 |
+
0.95
|
| 268 |
+
],
|
| 269 |
+
"eps": 1e-08,
|
| 270 |
+
"weight_decay": 0.1,
|
| 271 |
+
"_CLASS_": "olmo_core.optim.adamw.AdamWConfig"
|
| 272 |
+
},
|
| 273 |
+
"max_grad_norm": 0.5,
|
| 274 |
+
"scheduler": {
|
| 275 |
+
"lr_field": "lr",
|
| 276 |
+
"initial_lr_field": "initial_lr",
|
| 277 |
+
"units": "steps",
|
| 278 |
+
"alpha_f": 0.0,
|
| 279 |
+
"warmup_fraction": 0.1,
|
| 280 |
+
"warmup_min_lr": 0.0,
|
| 281 |
+
"_CLASS_": "olmo_core.optim.scheduler.LinearWithWarmup"
|
| 282 |
+
},
|
| 283 |
+
"compile_model": true,
|
| 284 |
+
"float8_config": {
|
| 285 |
+
"enabled": false,
|
| 286 |
+
"_CLASS_": "olmo_core.float8.Float8Config"
|
| 287 |
+
},
|
| 288 |
+
"dp_config": {
|
| 289 |
+
"name": "fsdp",
|
| 290 |
+
"param_dtype": "bfloat16",
|
| 291 |
+
"reduce_dtype": "float32",
|
| 292 |
+
"wrapping_strategy": "full",
|
| 293 |
+
"prefetch_factor": 0,
|
| 294 |
+
"_CLASS_": "olmo_core.train.train_module.transformer.config.TransformerDataParallelConfig"
|
| 295 |
+
},
|
| 296 |
+
"bolmo_config": {
|
| 297 |
+
"tokenizer": {
|
| 298 |
+
"vocab_size": 520,
|
| 299 |
+
"eos_token_id": 1,
|
| 300 |
+
"pad_token_id": 0,
|
| 301 |
+
"bos_token_id": 1,
|
| 302 |
+
"special_tokens": [
|
| 303 |
+
"<pad>",
|
| 304 |
+
"<bos>",
|
| 305 |
+
"<eos>",
|
| 306 |
+
"<bpe_token_end>"
|
| 307 |
+
],
|
| 308 |
+
"special_tokens_first": true,
|
| 309 |
+
"original_identifier": "allenai/dolma2-tokenizer",
|
| 310 |
+
"bpe_token_end_id": 3,
|
| 311 |
+
"_CLASS_": "olmo_core.data.tokenizer.ByteTokenizerConfig"
|
| 312 |
+
},
|
| 313 |
+
"losses": [
|
| 314 |
+
"ce",
|
| 315 |
+
"boundary"
|
| 316 |
+
],
|
| 317 |
+
"loss_weights": [
|
| 318 |
+
1.0,
|
| 319 |
+
4.0
|
| 320 |
+
],
|
| 321 |
+
"binarization_temp": 1.0,
|
| 322 |
+
"temperature": 1.0,
|
| 323 |
+
"div_fn": "tvd_temp_limit",
|
| 324 |
+
"boundary_mode": "end",
|
| 325 |
+
"merge_boundary_loss": false,
|
| 326 |
+
"use_output_boundary_jsd": false,
|
| 327 |
+
"eval_add_boundary_logp": false,
|
| 328 |
+
"do_alm_debiasing": false,
|
| 329 |
+
"rep_compare_fn": "l2",
|
| 330 |
+
"start_ratio": 4.3,
|
| 331 |
+
"target_ratio": 4.3,
|
| 332 |
+
"gradual_boundary_compression_steps": 150000,
|
| 333 |
+
"encoder_loss_lookahead": 0,
|
| 334 |
+
"encoder_loss_no_lookahead_weight": 1.0,
|
| 335 |
+
"encoder_loss_lookahead_weights": [],
|
| 336 |
+
"patching": "dolma2",
|
| 337 |
+
"epsilon": 1e-06,
|
| 338 |
+
"skip_blocks": false,
|
| 339 |
+
"skip_teacher_blocks": false,
|
| 340 |
+
"skip_teacher": true,
|
| 341 |
+
"compute_teacher_ce": false,
|
| 342 |
+
"use_student_patch_reps_for_teacher": false,
|
| 343 |
+
"use_oracle_patch_reps": false,
|
| 344 |
+
"teacher_blocks_no_grad": true,
|
| 345 |
+
"student_blocks_no_grad": false,
|
| 346 |
+
"decoder_backprop_through_encoder": true,
|
| 347 |
+
"decoder_backprop_through_boundary_predictor": true,
|
| 348 |
+
"boundary_predictor_backprop_through_encoder": true,
|
| 349 |
+
"teacher_force_boundaries": false,
|
| 350 |
+
"boundary_threshold": "sample:0",
|
| 351 |
+
"xlstm_igate_bias_init": -10.0,
|
| 352 |
+
"skip_boundary_before_eos": true,
|
| 353 |
+
"_CLASS_": "olmo_core.nn.bolmo.config.BolmoConfig"
|
| 354 |
+
},
|
| 355 |
+
"label_ignore_index": -100,
|
| 356 |
+
"_CLASS_": "olmo_core.train.train_module.transformer.config.TransformerTrainModuleConfig"
|
| 357 |
+
},
|
| 358 |
+
"trainer": {},
|
| 359 |
+
"init_seed": 12536,
|
| 360 |
+
"_CLASS_": "__main__.ExperimentConfig"
|
| 361 |
+
}
|
olmo_core/model_and_optim/.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d226d4df3f8b40ba639641867a687cad7cf295ab52e3efcdc1aadb38a275054f
|
| 3 |
+
size 9450495
|
olmo_core/model_and_optim/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fde3916824ea77107fe98a10cd264cbf48cfc786abfb433740460a0003ea6a1
|
| 3 |
+
size 179234958
|
olmo_core/model_and_optim/__0_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10980e12c3db08d331302e306468cc0377ba625b1a4092d82fbd1bcdc4899659
|
| 3 |
+
size 179234958
|
olmo_core/model_and_optim/__0_10.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:556ce5527abdfe9790dba105a0a56396f89f505b13ca92366f3b389451dbc928
|
| 3 |
+
size 179672297
|
olmo_core/model_and_optim/__0_11.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fab5a12c2161877514ec0a5f6d13897d19a90b49a892cdeed0ef49a9e1247906
|
| 3 |
+
size 179672297
|
olmo_core/model_and_optim/__0_12.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e14c0a4f7c1f46e41e3ee187e65a513966de7a237cc555662e6d13b651a983fc
|
| 3 |
+
size 179280658
|
olmo_core/model_and_optim/__0_13.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4d1e8af43fa91f5972d537bce7397c73e16930d4615ab03839af4a79945b45f
|
| 3 |
+
size 179280658
|
olmo_core/model_and_optim/__0_14.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b790e6f14a76309144a942046be664dd21489fff9014d8bdc82fabe53fe7b646
|
| 3 |
+
size 180056746
|
olmo_core/model_and_optim/__0_15.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a97a37b6df0446af12dcb6301bbe7a7af8c864361a086b3121930981d6f2ce7f
|
| 3 |
+
size 180055169
|
olmo_core/model_and_optim/__0_2.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18a1c51f2b7ba82c1cc633c4f4305c71a2ea178ba7cddf6f55b4e2672a62adc7
|
| 3 |
+
size 179236535
|
olmo_core/model_and_optim/__0_3.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1637ee8cd584c7186271c88473a45e8a9055c7fedd159c9d084c8b58753706c5
|
| 3 |
+
size 179345878
|
olmo_core/model_and_optim/__0_4.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40b8b057823abbee8227b5b9b0c493defdf5f77b71847f5859533a254d08bf11
|
| 3 |
+
size 179344617
|
olmo_core/model_and_optim/__0_5.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e9bbec4a5a7282e2e69857efde14becefab09b82c04b687d58042e3122b9d2a
|
| 3 |
+
size 179344617
|
olmo_core/model_and_optim/__0_6.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83bbf408da0a0ab10c4e9c69f23b9db392911a11e8d9e649060e446d52d590f4
|
| 3 |
+
size 179672297
|
olmo_core/model_and_optim/__0_7.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca5bc3ab73fef5efc91a7f2311dca3741be6e9456bd1365bf37250e58ffb0263
|
| 3 |
+
size 179672297
|
olmo_core/model_and_optim/__0_8.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c04b53514e3fc2ec72789ce8b6cf4cf303056efa07c7aa0e3b757af8faf8be2d
|
| 3 |
+
size 179672297
|
olmo_core/model_and_optim/__0_9.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a05df82c033265d09355a5896191c6032b61b6c1e473dfdfa6db4089c3c8aa6
|
| 3 |
+
size 179672297
|
olmo_core/model_and_optim/__10_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbb5fac97c9b75ec68cf760f6c9b9318d16604691f68fc1b97889268937cb93f
|
| 3 |
+
size 178818828
|
olmo_core/model_and_optim/__10_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:569a71c136e97d2746545a32addb7127b0b1d071437bdea1ae924c15c013d9f2
|
| 3 |
+
size 178818828
|
olmo_core/model_and_optim/__10_10.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c1757135ce728caecb55e79a83eededc9d7d432c3440dcff76be32f4feebe18
|
| 3 |
+
size 179257428
|
olmo_core/model_and_optim/__10_11.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c8d3632eb2c3112095bc1b844af4c922afff5623c2168cda3713f87e420fa5e
|
| 3 |
+
size 179257428
|
olmo_core/model_and_optim/__10_12.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb8caef839b9d1bf84959c53c64bfb3f85f82708ffe6a96d8317326d88e60f15
|
| 3 |
+
size 178865789
|
olmo_core/model_and_optim/__10_13.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86017597935cf303efd55164064aa86a180a41576a34f47039627a5c4a156d45
|
| 3 |
+
size 178865789
|
olmo_core/model_and_optim/__10_14.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e9cc0aedad97f6f8c6c9eb14b791220c353d9fd02476213d95141aa40aee4b7
|
| 3 |
+
size 179294937
|
olmo_core/model_and_optim/__10_15.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de14d46b4098bc6a5e4e911f9bd479a9871bb99d7237a914d2590f9866251d89
|
| 3 |
+
size 179294937
|
olmo_core/model_and_optim/__10_2.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10f4f79877a2121215d81cb18a4dc5429390eaa6b39bd9566c69908008c654cf
|
| 3 |
+
size 178820405
|
olmo_core/model_and_optim/__10_3.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f116a86923d2096a055aafd1e520f9b61e5c6796578c8415b56f4a85f92c45b0
|
| 3 |
+
size 178929748
|
olmo_core/model_and_optim/__10_4.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3eae74a28adb5e9c57bc924fbba1205a423e6488f3ba89c62cc3b7f7694a1da1
|
| 3 |
+
size 178929748
|
olmo_core/model_and_optim/__10_5.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cc74c4ea7f53200e309217958585660d18665e920730e5076082d04a6484a05
|
| 3 |
+
size 178929748
|
olmo_core/model_and_optim/__10_6.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ff41964b709da0d9e5a17e38c9a44ed00aa6cf20a412e17a9522b3b7377ac29
|
| 3 |
+
size 179257428
|
olmo_core/model_and_optim/__10_7.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c06b8804f9d426d55ce0683baf08b5fec2015c4771137609a1ec933d01a58fb8
|
| 3 |
+
size 179257428
|
olmo_core/model_and_optim/__10_8.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d018b5f2ff0b158574a00ccd1106ca6df8a0a8a829b0a509b76ac88937ca311
|
| 3 |
+
size 179257428
|
olmo_core/model_and_optim/__10_9.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e1312e5cd760fd83c909b20d3b430c1488112a39c7057d6b2298e34503570b6
|
| 3 |
+
size 179257428
|
olmo_core/model_and_optim/__11_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f55336df7daef34ed8ffaeac38da44ae6c65111665821411305869a2ea17ca95
|
| 3 |
+
size 178818828
|
olmo_core/model_and_optim/__11_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1290ebf674851c99ade037dfd8e628906396a2e1c49b7f5e6ce943c8e90dcc3
|
| 3 |
+
size 178818828
|
olmo_core/model_and_optim/__11_10.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11c5895fda2bc149ce8c4b532a8f3698873087326fc26093dfc6c1291fc16b0c
|
| 3 |
+
size 179257428
|
olmo_core/model_and_optim/__11_11.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f9a6a095e3fa712117ec5de5ebbad6cf0e7ac482a7b429b341ab7243ee2a499
|
| 3 |
+
size 179257428
|
olmo_core/model_and_optim/__11_12.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:749e9683ef7ab1cbceffe47b5d2c2e1ddf0c270fd1bcd2e739350c515cf2fb8e
|
| 3 |
+
size 178865789
|
olmo_core/model_and_optim/__11_13.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ac0b3c96fa5b4b7de7be230e4b377ab0e884b565c281c58c92f74015effc21c
|
| 3 |
+
size 178865789
|
olmo_core/model_and_optim/__11_14.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:609775f6385e0f6ca2b4765b328730fd314e24f5dd14443449159c6d0ab7c2bb
|
| 3 |
+
size 179294937
|
olmo_core/model_and_optim/__11_15.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ccb1922d13ad5112b32010f868fb70cab17ea8e1171911aa96d350b659dd344
|
| 3 |
+
size 179294937
|
olmo_core/model_and_optim/__11_2.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e7fdac412f40813a7e73205770e612f355f25a3a546ae6d0f0708747a84be18
|
| 3 |
+
size 178820405
|
olmo_core/model_and_optim/__11_3.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b34429d67974a376317b3b60e1f32c0561d5428f3348ef6e013ddaef683c25ac
|
| 3 |
+
size 178929748
|
olmo_core/model_and_optim/__11_4.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b8c66fa5e2d3387017972391fb28d02577951c3040f33fb68d6c08fc18e3ca4
|
| 3 |
+
size 178929748
|
olmo_core/model_and_optim/__11_5.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dd8b974d7a4fa4ef8478057b6075ccb524c3dbc82f5fef650c922bb35c03a1a
|
| 3 |
+
size 178929748
|
olmo_core/model_and_optim/__11_6.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f204ddb999a622d73b9a72e02e94fe6ab9a62f57b97752237d1cd93cf9cdf259
|
| 3 |
+
size 179257428
|
olmo_core/model_and_optim/__11_7.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:297de0e482eda03814b1505476278af6106ad65850b86cc4a2e8314a3de72a55
|
| 3 |
+
size 179257428
|