Uploading folder deepscaler_models to hf tyzhu/deepscaler_modelsat time 2025-03-09 07:00:50
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +150 -0
- deepscaler-1.5b-8k/actor/global_step_100/config.json +31 -0
- deepscaler-1.5b-8k/actor/global_step_100/generation_config.json +9 -0
- deepscaler-1.5b-8k/actor/global_step_100/model-00001-of-00002.safetensors +3 -0
- deepscaler-1.5b-8k/actor/global_step_100/model-00002-of-00002.safetensors +3 -0
- deepscaler-1.5b-8k/actor/global_step_100/model.safetensors.index.json +346 -0
- deepscaler-1.5b-8k/actor/global_step_100/special_tokens_map.json +23 -0
- deepscaler-1.5b-8k/actor/global_step_100/tokenizer.json +3 -0
- deepscaler-1.5b-8k/actor/global_step_100/tokenizer_config.json +195 -0
- deepscaler-1.5b-8k/actor/global_step_1000/config.json +31 -0
- deepscaler-1.5b-8k/actor/global_step_1000/generation_config.json +9 -0
- deepscaler-1.5b-8k/actor/global_step_1000/model-00001-of-00002.safetensors +3 -0
- deepscaler-1.5b-8k/actor/global_step_1000/model-00002-of-00002.safetensors +3 -0
- deepscaler-1.5b-8k/actor/global_step_1000/model.safetensors.index.json +346 -0
- deepscaler-1.5b-8k/actor/global_step_1000/special_tokens_map.json +23 -0
- deepscaler-1.5b-8k/actor/global_step_1000/tokenizer.json +3 -0
- deepscaler-1.5b-8k/actor/global_step_1000/tokenizer_config.json +195 -0
- deepscaler-1.5b-8k/actor/global_step_1020/config.json +31 -0
- deepscaler-1.5b-8k/actor/global_step_1020/generation_config.json +9 -0
- deepscaler-1.5b-8k/actor/global_step_1020/model-00001-of-00002.safetensors +3 -0
- deepscaler-1.5b-8k/actor/global_step_1020/model-00002-of-00002.safetensors +3 -0
- deepscaler-1.5b-8k/actor/global_step_1020/model.safetensors.index.json +346 -0
- deepscaler-1.5b-8k/actor/global_step_1020/special_tokens_map.json +23 -0
- deepscaler-1.5b-8k/actor/global_step_1020/tokenizer.json +3 -0
- deepscaler-1.5b-8k/actor/global_step_1020/tokenizer_config.json +195 -0
- deepscaler-1.5b-8k/actor/global_step_1040/config.json +31 -0
- deepscaler-1.5b-8k/actor/global_step_1040/generation_config.json +9 -0
- deepscaler-1.5b-8k/actor/global_step_1040/model-00001-of-00002.safetensors +3 -0
- deepscaler-1.5b-8k/actor/global_step_1040/model-00002-of-00002.safetensors +3 -0
- deepscaler-1.5b-8k/actor/global_step_1040/model.safetensors.index.json +346 -0
- deepscaler-1.5b-8k/actor/global_step_1040/special_tokens_map.json +23 -0
- deepscaler-1.5b-8k/actor/global_step_1040/tokenizer.json +3 -0
- deepscaler-1.5b-8k/actor/global_step_1040/tokenizer_config.json +195 -0
- deepscaler-1.5b-8k/actor/global_step_1060/config.json +31 -0
- deepscaler-1.5b-8k/actor/global_step_1060/generation_config.json +9 -0
- deepscaler-1.5b-8k/actor/global_step_1060/model-00001-of-00002.safetensors +3 -0
- deepscaler-1.5b-8k/actor/global_step_1060/model-00002-of-00002.safetensors +3 -0
- deepscaler-1.5b-8k/actor/global_step_1060/model.safetensors.index.json +346 -0
- deepscaler-1.5b-8k/actor/global_step_1060/special_tokens_map.json +23 -0
- deepscaler-1.5b-8k/actor/global_step_1060/tokenizer.json +3 -0
- deepscaler-1.5b-8k/actor/global_step_1060/tokenizer_config.json +195 -0
- deepscaler-1.5b-8k/actor/global_step_1080/config.json +31 -0
- deepscaler-1.5b-8k/actor/global_step_1080/generation_config.json +9 -0
- deepscaler-1.5b-8k/actor/global_step_1080/model-00001-of-00002.safetensors +3 -0
- deepscaler-1.5b-8k/actor/global_step_1080/model-00002-of-00002.safetensors +3 -0
- deepscaler-1.5b-8k/actor/global_step_1080/model.safetensors.index.json +346 -0
- deepscaler-1.5b-8k/actor/global_step_1080/special_tokens_map.json +23 -0
- deepscaler-1.5b-8k/actor/global_step_1080/tokenizer.json +3 -0
- deepscaler-1.5b-8k/actor/global_step_1080/tokenizer_config.json +195 -0
- deepscaler-1.5b-8k/actor/global_step_1100/config.json +31 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,153 @@ 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 |
+
deepscaler-1.5b-8k/actor/global_step_100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
deepscaler-1.5b-8k/actor/global_step_1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
deepscaler-1.5b-8k/actor/global_step_1020/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
deepscaler-1.5b-8k/actor/global_step_1040/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
deepscaler-1.5b-8k/actor/global_step_1060/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
deepscaler-1.5b-8k/actor/global_step_1080/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
deepscaler-1.5b-8k/actor/global_step_1100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
deepscaler-1.5b-8k/actor/global_step_1120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
deepscaler-1.5b-8k/actor/global_step_1140/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
deepscaler-1.5b-8k/actor/global_step_1160/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
deepscaler-1.5b-8k/actor/global_step_1180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
deepscaler-1.5b-8k/actor/global_step_120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
deepscaler-1.5b-8k/actor/global_step_1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
deepscaler-1.5b-8k/actor/global_step_1220/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
deepscaler-1.5b-8k/actor/global_step_1240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
deepscaler-1.5b-8k/actor/global_step_1260/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
deepscaler-1.5b-8k/actor/global_step_1280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
deepscaler-1.5b-8k/actor/global_step_1300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
deepscaler-1.5b-8k/actor/global_step_1320/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
deepscaler-1.5b-8k/actor/global_step_1340/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
deepscaler-1.5b-8k/actor/global_step_1360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
deepscaler-1.5b-8k/actor/global_step_1380/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
deepscaler-1.5b-8k/actor/global_step_140/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 59 |
+
deepscaler-1.5b-8k/actor/global_step_1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 60 |
+
deepscaler-1.5b-8k/actor/global_step_1420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 61 |
+
deepscaler-1.5b-8k/actor/global_step_1440/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
deepscaler-1.5b-8k/actor/global_step_1460/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 63 |
+
deepscaler-1.5b-8k/actor/global_step_1480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 64 |
+
deepscaler-1.5b-8k/actor/global_step_1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 65 |
+
deepscaler-1.5b-8k/actor/global_step_1520/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 66 |
+
deepscaler-1.5b-8k/actor/global_step_1540/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 67 |
+
deepscaler-1.5b-8k/actor/global_step_1560/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 68 |
+
deepscaler-1.5b-8k/actor/global_step_1580/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 69 |
+
deepscaler-1.5b-8k/actor/global_step_160/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 70 |
+
deepscaler-1.5b-8k/actor/global_step_1600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 71 |
+
deepscaler-1.5b-8k/actor/global_step_1620/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 72 |
+
deepscaler-1.5b-8k/actor/global_step_1640/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 73 |
+
deepscaler-1.5b-8k/actor/global_step_1660/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 74 |
+
deepscaler-1.5b-8k/actor/global_step_1680/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 75 |
+
deepscaler-1.5b-8k/actor/global_step_1700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 76 |
+
deepscaler-1.5b-8k/actor/global_step_1720/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 77 |
+
deepscaler-1.5b-8k/actor/global_step_1740/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 78 |
+
deepscaler-1.5b-8k/actor/global_step_1760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 79 |
+
deepscaler-1.5b-8k/actor/global_step_1780/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 80 |
+
deepscaler-1.5b-8k/actor/global_step_180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 81 |
+
deepscaler-1.5b-8k/actor/global_step_1800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 82 |
+
deepscaler-1.5b-8k/actor/global_step_1820/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 83 |
+
deepscaler-1.5b-8k/actor/global_step_1840/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 84 |
+
deepscaler-1.5b-8k/actor/global_step_1860/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 85 |
+
deepscaler-1.5b-8k/actor/global_step_1880/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 86 |
+
deepscaler-1.5b-8k/actor/global_step_1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 87 |
+
deepscaler-1.5b-8k/actor/global_step_1920/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 88 |
+
deepscaler-1.5b-8k/actor/global_step_1940/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 89 |
+
deepscaler-1.5b-8k/actor/global_step_1960/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 90 |
+
deepscaler-1.5b-8k/actor/global_step_1980/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 91 |
+
deepscaler-1.5b-8k/actor/global_step_20/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 92 |
+
deepscaler-1.5b-8k/actor/global_step_200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 93 |
+
deepscaler-1.5b-8k/actor/global_step_2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 94 |
+
deepscaler-1.5b-8k/actor/global_step_2020/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 95 |
+
deepscaler-1.5b-8k/actor/global_step_2040/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 96 |
+
deepscaler-1.5b-8k/actor/global_step_2060/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 97 |
+
deepscaler-1.5b-8k/actor/global_step_2080/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 98 |
+
deepscaler-1.5b-8k/actor/global_step_2100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 99 |
+
deepscaler-1.5b-8k/actor/global_step_2120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 100 |
+
deepscaler-1.5b-8k/actor/global_step_2140/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 101 |
+
deepscaler-1.5b-8k/actor/global_step_2160/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 102 |
+
deepscaler-1.5b-8k/actor/global_step_2180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 103 |
+
deepscaler-1.5b-8k/actor/global_step_220/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 104 |
+
deepscaler-1.5b-8k/actor/global_step_2200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 105 |
+
deepscaler-1.5b-8k/actor/global_step_2220/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 106 |
+
deepscaler-1.5b-8k/actor/global_step_2240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 107 |
+
deepscaler-1.5b-8k/actor/global_step_2260/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 108 |
+
deepscaler-1.5b-8k/actor/global_step_2280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 109 |
+
deepscaler-1.5b-8k/actor/global_step_2300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 110 |
+
deepscaler-1.5b-8k/actor/global_step_2320/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 111 |
+
deepscaler-1.5b-8k/actor/global_step_2340/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 112 |
+
deepscaler-1.5b-8k/actor/global_step_2360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 113 |
+
deepscaler-1.5b-8k/actor/global_step_2380/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 114 |
+
deepscaler-1.5b-8k/actor/global_step_240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 115 |
+
deepscaler-1.5b-8k/actor/global_step_2400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 116 |
+
deepscaler-1.5b-8k/actor/global_step_2420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 117 |
+
deepscaler-1.5b-8k/actor/global_step_2440/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 118 |
+
deepscaler-1.5b-8k/actor/global_step_2460/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 119 |
+
deepscaler-1.5b-8k/actor/global_step_2480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 120 |
+
deepscaler-1.5b-8k/actor/global_step_2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 121 |
+
deepscaler-1.5b-8k/actor/global_step_2520/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 122 |
+
deepscaler-1.5b-8k/actor/global_step_2540/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 123 |
+
deepscaler-1.5b-8k/actor/global_step_2560/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 124 |
+
deepscaler-1.5b-8k/actor/global_step_2580/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 125 |
+
deepscaler-1.5b-8k/actor/global_step_260/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 126 |
+
deepscaler-1.5b-8k/actor/global_step_2600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 127 |
+
deepscaler-1.5b-8k/actor/global_step_2620/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 128 |
+
deepscaler-1.5b-8k/actor/global_step_2640/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 129 |
+
deepscaler-1.5b-8k/actor/global_step_2660/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 130 |
+
deepscaler-1.5b-8k/actor/global_step_2680/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 131 |
+
deepscaler-1.5b-8k/actor/global_step_2700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 132 |
+
deepscaler-1.5b-8k/actor/global_step_2720/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 133 |
+
deepscaler-1.5b-8k/actor/global_step_2740/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 134 |
+
deepscaler-1.5b-8k/actor/global_step_2760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 135 |
+
deepscaler-1.5b-8k/actor/global_step_2780/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 136 |
+
deepscaler-1.5b-8k/actor/global_step_280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 137 |
+
deepscaler-1.5b-8k/actor/global_step_2800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 138 |
+
deepscaler-1.5b-8k/actor/global_step_2820/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 139 |
+
deepscaler-1.5b-8k/actor/global_step_2840/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 140 |
+
deepscaler-1.5b-8k/actor/global_step_2860/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 141 |
+
deepscaler-1.5b-8k/actor/global_step_2880/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 142 |
+
deepscaler-1.5b-8k/actor/global_step_2900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 143 |
+
deepscaler-1.5b-8k/actor/global_step_2920/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 144 |
+
deepscaler-1.5b-8k/actor/global_step_2940/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 145 |
+
deepscaler-1.5b-8k/actor/global_step_2960/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 146 |
+
deepscaler-1.5b-8k/actor/global_step_2980/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 147 |
+
deepscaler-1.5b-8k/actor/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 148 |
+
deepscaler-1.5b-8k/actor/global_step_3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 149 |
+
deepscaler-1.5b-8k/actor/global_step_320/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 150 |
+
deepscaler-1.5b-8k/actor/global_step_340/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 151 |
+
deepscaler-1.5b-8k/actor/global_step_360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 152 |
+
deepscaler-1.5b-8k/actor/global_step_380/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 153 |
+
deepscaler-1.5b-8k/actor/global_step_40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 154 |
+
deepscaler-1.5b-8k/actor/global_step_400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 155 |
+
deepscaler-1.5b-8k/actor/global_step_420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 156 |
+
deepscaler-1.5b-8k/actor/global_step_440/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 157 |
+
deepscaler-1.5b-8k/actor/global_step_460/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 158 |
+
deepscaler-1.5b-8k/actor/global_step_480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 159 |
+
deepscaler-1.5b-8k/actor/global_step_500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 160 |
+
deepscaler-1.5b-8k/actor/global_step_520/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 161 |
+
deepscaler-1.5b-8k/actor/global_step_540/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 162 |
+
deepscaler-1.5b-8k/actor/global_step_560/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 163 |
+
deepscaler-1.5b-8k/actor/global_step_580/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 164 |
+
deepscaler-1.5b-8k/actor/global_step_60/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 165 |
+
deepscaler-1.5b-8k/actor/global_step_600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 166 |
+
deepscaler-1.5b-8k/actor/global_step_620/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 167 |
+
deepscaler-1.5b-8k/actor/global_step_640/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 168 |
+
deepscaler-1.5b-8k/actor/global_step_660/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 169 |
+
deepscaler-1.5b-8k/actor/global_step_680/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 170 |
+
deepscaler-1.5b-8k/actor/global_step_700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 171 |
+
deepscaler-1.5b-8k/actor/global_step_720/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 172 |
+
deepscaler-1.5b-8k/actor/global_step_740/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 173 |
+
deepscaler-1.5b-8k/actor/global_step_760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 174 |
+
deepscaler-1.5b-8k/actor/global_step_780/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 175 |
+
deepscaler-1.5b-8k/actor/global_step_80/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 176 |
+
deepscaler-1.5b-8k/actor/global_step_800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 177 |
+
deepscaler-1.5b-8k/actor/global_step_820/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 178 |
+
deepscaler-1.5b-8k/actor/global_step_840/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 179 |
+
deepscaler-1.5b-8k/actor/global_step_860/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 180 |
+
deepscaler-1.5b-8k/actor/global_step_880/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 181 |
+
deepscaler-1.5b-8k/actor/global_step_900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 182 |
+
deepscaler-1.5b-8k/actor/global_step_920/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 183 |
+
deepscaler-1.5b-8k/actor/global_step_940/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 184 |
+
deepscaler-1.5b-8k/actor/global_step_960/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 185 |
+
deepscaler-1.5b-8k/actor/global_step_980/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
deepscaler-1.5b-8k/actor/global_step_100/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151646,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1536,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8960,
|
| 13 |
+
"max_position_embeddings": 131072,
|
| 14 |
+
"max_window_layers": 21,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"pad_token_id": 151643,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.47.1",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_mrope": false,
|
| 29 |
+
"use_sliding_window": false,
|
| 30 |
+
"vocab_size": 151936
|
| 31 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_100/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151646,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 151643,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.47.1"
|
| 9 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_100/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91d1a619a92a6a6b9c0170be2c1d5e302884d0cd5441eac9391b9c3fb39d6aa8
|
| 3 |
+
size 4996670464
|
deepscaler-1.5b-8k/actor/global_step_100/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73f4df56ccfe85d868610f7cb50ba9779d4869f6ac1547c8f3992fafc3d850bf
|
| 3 |
+
size 2111719976
|
deepscaler-1.5b-8k/actor/global_step_100/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 7108352000
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 345 |
+
}
|
| 346 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_100/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
|
| 3 |
+
size 11422778
|
deepscaler-1.5b-8k/actor/global_step_100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<｜User｜>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<｜Assistant｜>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|EOT|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<think>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "</think>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 187 |
+
"extra_special_tokens": {},
|
| 188 |
+
"legacy": true,
|
| 189 |
+
"model_max_length": 16384,
|
| 190 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 193 |
+
"unk_token": null,
|
| 194 |
+
"use_default_system_prompt": false
|
| 195 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151646,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1536,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8960,
|
| 13 |
+
"max_position_embeddings": 131072,
|
| 14 |
+
"max_window_layers": 21,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"pad_token_id": 151643,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.47.1",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_mrope": false,
|
| 29 |
+
"use_sliding_window": false,
|
| 30 |
+
"vocab_size": 151936
|
| 31 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1000/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151646,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 151643,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.47.1"
|
| 9 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1000/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a574322ac101a3ac66fcb8cf1ccfb07d1a0bd6f1069d08f7610979e71e99fff8
|
| 3 |
+
size 4996670464
|
deepscaler-1.5b-8k/actor/global_step_1000/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ff751b1c83ec3b7c144aeb62b254e901df8a7a5518ecccc0c7f5f4274870e23
|
| 3 |
+
size 2111719976
|
deepscaler-1.5b-8k/actor/global_step_1000/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 7108352000
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 345 |
+
}
|
| 346 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
|
| 3 |
+
size 11422778
|
deepscaler-1.5b-8k/actor/global_step_1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<｜User｜>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<｜Assistant｜>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|EOT|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<think>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "</think>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 187 |
+
"extra_special_tokens": {},
|
| 188 |
+
"legacy": true,
|
| 189 |
+
"model_max_length": 16384,
|
| 190 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 193 |
+
"unk_token": null,
|
| 194 |
+
"use_default_system_prompt": false
|
| 195 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1020/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151646,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1536,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8960,
|
| 13 |
+
"max_position_embeddings": 131072,
|
| 14 |
+
"max_window_layers": 21,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"pad_token_id": 151643,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.47.1",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_mrope": false,
|
| 29 |
+
"use_sliding_window": false,
|
| 30 |
+
"vocab_size": 151936
|
| 31 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1020/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151646,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 151643,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.47.1"
|
| 9 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1020/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06f5084e22d07b991c2350e0275f6c9fc7f9ba3f95b89a6d815b76bf2ba6bce0
|
| 3 |
+
size 4996670464
|
deepscaler-1.5b-8k/actor/global_step_1020/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a04fec425fa3599990ba30cad1965dc84eebe7fce45b809645024c91125ee0d9
|
| 3 |
+
size 2111719976
|
deepscaler-1.5b-8k/actor/global_step_1020/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 7108352000
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 345 |
+
}
|
| 346 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1020/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1020/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
|
| 3 |
+
size 11422778
|
deepscaler-1.5b-8k/actor/global_step_1020/tokenizer_config.json
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<｜User｜>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<｜Assistant｜>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|EOT|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<think>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "</think>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 187 |
+
"extra_special_tokens": {},
|
| 188 |
+
"legacy": true,
|
| 189 |
+
"model_max_length": 16384,
|
| 190 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 193 |
+
"unk_token": null,
|
| 194 |
+
"use_default_system_prompt": false
|
| 195 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1040/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151646,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1536,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8960,
|
| 13 |
+
"max_position_embeddings": 131072,
|
| 14 |
+
"max_window_layers": 21,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"pad_token_id": 151643,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.47.1",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_mrope": false,
|
| 29 |
+
"use_sliding_window": false,
|
| 30 |
+
"vocab_size": 151936
|
| 31 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1040/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151646,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 151643,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.47.1"
|
| 9 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1040/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fee44e4f7b49092a8dffd374ac5ea69b7c20bc0d636c721a74837007fb42efa
|
| 3 |
+
size 4996670464
|
deepscaler-1.5b-8k/actor/global_step_1040/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c4125ac120f48d113a4c979d6ac591dc8b10839c1d6bb3b0f941316c5379b21
|
| 3 |
+
size 2111719976
|
deepscaler-1.5b-8k/actor/global_step_1040/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 7108352000
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 345 |
+
}
|
| 346 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1040/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1040/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
|
| 3 |
+
size 11422778
|
deepscaler-1.5b-8k/actor/global_step_1040/tokenizer_config.json
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<｜User｜>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<｜Assistant｜>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|EOT|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<think>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "</think>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 187 |
+
"extra_special_tokens": {},
|
| 188 |
+
"legacy": true,
|
| 189 |
+
"model_max_length": 16384,
|
| 190 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 193 |
+
"unk_token": null,
|
| 194 |
+
"use_default_system_prompt": false
|
| 195 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1060/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151646,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1536,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8960,
|
| 13 |
+
"max_position_embeddings": 131072,
|
| 14 |
+
"max_window_layers": 21,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"pad_token_id": 151643,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.47.1",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_mrope": false,
|
| 29 |
+
"use_sliding_window": false,
|
| 30 |
+
"vocab_size": 151936
|
| 31 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1060/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151646,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 151643,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.47.1"
|
| 9 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1060/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8e8e5ca7115a493ada94125e3aa356c435fc636205c62a747d1d7038a7a7292
|
| 3 |
+
size 4996670464
|
deepscaler-1.5b-8k/actor/global_step_1060/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4682093ac6789553dc0e6f95bf66fcc2d064b949e2a70b697ec84874e0ab4da
|
| 3 |
+
size 2111719976
|
deepscaler-1.5b-8k/actor/global_step_1060/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 7108352000
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 345 |
+
}
|
| 346 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1060/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1060/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
|
| 3 |
+
size 11422778
|
deepscaler-1.5b-8k/actor/global_step_1060/tokenizer_config.json
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<｜User｜>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<｜Assistant｜>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|EOT|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<think>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "</think>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 187 |
+
"extra_special_tokens": {},
|
| 188 |
+
"legacy": true,
|
| 189 |
+
"model_max_length": 16384,
|
| 190 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 193 |
+
"unk_token": null,
|
| 194 |
+
"use_default_system_prompt": false
|
| 195 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1080/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151646,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1536,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8960,
|
| 13 |
+
"max_position_embeddings": 131072,
|
| 14 |
+
"max_window_layers": 21,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"pad_token_id": 151643,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.47.1",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_mrope": false,
|
| 29 |
+
"use_sliding_window": false,
|
| 30 |
+
"vocab_size": 151936
|
| 31 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1080/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151646,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 151643,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.47.1"
|
| 9 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1080/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dee58d0545f82cfa0e52b073364cfbd0a83c253de5a1a27c7bdccf5ce9c52d28
|
| 3 |
+
size 4996670464
|
deepscaler-1.5b-8k/actor/global_step_1080/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1b19765e7e99f98157dfedcce5c12f02a196960110e9aa5c860ef6a64718755
|
| 3 |
+
size 2111719976
|
deepscaler-1.5b-8k/actor/global_step_1080/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 7108352000
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 345 |
+
}
|
| 346 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1080/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1080/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
|
| 3 |
+
size 11422778
|
deepscaler-1.5b-8k/actor/global_step_1080/tokenizer_config.json
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"151643": {
|
| 7 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"151644": {
|
| 15 |
+
"content": "<｜User｜>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"151645": {
|
| 23 |
+
"content": "<｜Assistant｜>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"151646": {
|
| 31 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"151647": {
|
| 39 |
+
"content": "<|EOT|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"151648": {
|
| 47 |
+
"content": "<think>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"151649": {
|
| 55 |
+
"content": "</think>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"151650": {
|
| 63 |
+
"content": "<|quad_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"151651": {
|
| 71 |
+
"content": "<|quad_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"151652": {
|
| 79 |
+
"content": "<|vision_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"151653": {
|
| 87 |
+
"content": "<|vision_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"151654": {
|
| 95 |
+
"content": "<|vision_pad|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"151655": {
|
| 103 |
+
"content": "<|image_pad|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"151656": {
|
| 111 |
+
"content": "<|video_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"151657": {
|
| 119 |
+
"content": "<tool_call>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"151658": {
|
| 127 |
+
"content": "</tool_call>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"151659": {
|
| 135 |
+
"content": "<|fim_prefix|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"151660": {
|
| 143 |
+
"content": "<|fim_middle|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"151661": {
|
| 151 |
+
"content": "<|fim_suffix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"151662": {
|
| 159 |
+
"content": "<|fim_pad|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"151663": {
|
| 167 |
+
"content": "<|repo_name|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"151664": {
|
| 175 |
+
"content": "<|file_sep|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 187 |
+
"extra_special_tokens": {},
|
| 188 |
+
"legacy": true,
|
| 189 |
+
"model_max_length": 16384,
|
| 190 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 193 |
+
"unk_token": null,
|
| 194 |
+
"use_default_system_prompt": false
|
| 195 |
+
}
|
deepscaler-1.5b-8k/actor/global_step_1100/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151646,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1536,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8960,
|
| 13 |
+
"max_position_embeddings": 131072,
|
| 14 |
+
"max_window_layers": 21,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"pad_token_id": 151643,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.47.1",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_mrope": false,
|
| 29 |
+
"use_sliding_window": false,
|
| 30 |
+
"vocab_size": 151936
|
| 31 |
+
}
|