VoCuc commited on
Commit
21bb6eb
·
verified ·
1 Parent(s): 997313d

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +160 -0
  2. span_v3/ace_0_0.6B_cl/0/17/README.md +207 -0
  3. span_v3/ace_0_0.6B_cl/0/17/adapter_config.json +46 -0
  4. span_v3/ace_0_0.6B_cl/0/17/adapter_model.bin +3 -0
  5. span_v3/ace_0_0.6B_cl/0/17/added_tokens.json +28 -0
  6. span_v3/ace_0_0.6B_cl/0/17/chat_template.jinja +89 -0
  7. span_v3/ace_0_0.6B_cl/0/17/merges.txt +0 -0
  8. span_v3/ace_0_0.6B_cl/0/17/special_tokens_map.json +19 -0
  9. span_v3/ace_0_0.6B_cl/0/17/tokenizer.json +3 -0
  10. span_v3/ace_0_0.6B_cl/0/17/tokenizer_config.json +240 -0
  11. span_v3/ace_0_0.6B_cl/0/17/vocab.json +0 -0
  12. span_v3/ace_0_0.6B_cl/0/34/README.md +207 -0
  13. span_v3/ace_0_0.6B_cl/0/34/adapter_config.json +46 -0
  14. span_v3/ace_0_0.6B_cl/0/34/adapter_model.bin +3 -0
  15. span_v3/ace_0_0.6B_cl/0/34/added_tokens.json +28 -0
  16. span_v3/ace_0_0.6B_cl/0/34/chat_template.jinja +89 -0
  17. span_v3/ace_0_0.6B_cl/0/34/merges.txt +0 -0
  18. span_v3/ace_0_0.6B_cl/0/34/special_tokens_map.json +19 -0
  19. span_v3/ace_0_0.6B_cl/0/34/tokenizer.json +3 -0
  20. span_v3/ace_0_0.6B_cl/0/34/tokenizer_config.json +240 -0
  21. span_v3/ace_0_0.6B_cl/0/34/vocab.json +0 -0
  22. span_v3/ace_0_0.6B_cl/0/51/README.md +207 -0
  23. span_v3/ace_0_0.6B_cl/0/51/adapter_config.json +46 -0
  24. span_v3/ace_0_0.6B_cl/0/51/adapter_model.bin +3 -0
  25. span_v3/ace_0_0.6B_cl/0/51/added_tokens.json +28 -0
  26. span_v3/ace_0_0.6B_cl/0/51/chat_template.jinja +89 -0
  27. span_v3/ace_0_0.6B_cl/0/51/merges.txt +0 -0
  28. span_v3/ace_0_0.6B_cl/0/51/special_tokens_map.json +19 -0
  29. span_v3/ace_0_0.6B_cl/0/51/tokenizer.json +3 -0
  30. span_v3/ace_0_0.6B_cl/0/51/tokenizer_config.json +240 -0
  31. span_v3/ace_0_0.6B_cl/0/51/vocab.json +0 -0
  32. span_v3/ace_0_0.6B_cl/0/args.json +1 -0
  33. span_v3/ace_0_0.6B_cl/0/eval/0/answers.jsonl +98 -0
  34. span_v3/ace_0_0.6B_cl/0/eval/1/answers.jsonl +98 -0
  35. span_v3/ace_0_0.6B_cl/0/eval/2/answers.jsonl +98 -0
  36. span_v3/ace_0_0.6B_cl/0/log.txt +16 -0
  37. span_v3/ace_0_0.6B_cl/1/26/README.md +207 -0
  38. span_v3/ace_0_0.6B_cl/1/26/adapter_config.json +46 -0
  39. span_v3/ace_0_0.6B_cl/1/26/adapter_model.bin +3 -0
  40. span_v3/ace_0_0.6B_cl/1/26/added_tokens.json +28 -0
  41. span_v3/ace_0_0.6B_cl/1/26/chat_template.jinja +89 -0
  42. span_v3/ace_0_0.6B_cl/1/26/merges.txt +0 -0
  43. span_v3/ace_0_0.6B_cl/1/26/special_tokens_map.json +19 -0
  44. span_v3/ace_0_0.6B_cl/1/26/tokenizer.json +3 -0
  45. span_v3/ace_0_0.6B_cl/1/26/tokenizer_config.json +240 -0
  46. span_v3/ace_0_0.6B_cl/1/26/vocab.json +0 -0
  47. span_v3/ace_0_0.6B_cl/1/52/README.md +207 -0
  48. span_v3/ace_0_0.6B_cl/1/52/adapter_config.json +46 -0
  49. span_v3/ace_0_0.6B_cl/1/52/adapter_model.bin +3 -0
  50. span_v3/ace_0_0.6B_cl/1/52/added_tokens.json +28 -0
.gitattributes CHANGED
@@ -991,3 +991,163 @@ open-ed/A401_results/qwen3/sft_4B_cl_v2_1/3/81/tokenizer.json filter=lfs diff=lf
991
  open-ed/A401_results/qwen3/sft_4B_cl_v2_1/4/25/tokenizer.json filter=lfs diff=lfs merge=lfs -text
992
  open-ed/A401_results/qwen3/sft_4B_cl_v2_1/4/50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
993
  open-ed/A401_results/qwen3/sft_4B_cl_v2_1/4/75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
991
  open-ed/A401_results/qwen3/sft_4B_cl_v2_1/4/25/tokenizer.json filter=lfs diff=lfs merge=lfs -text
992
  open-ed/A401_results/qwen3/sft_4B_cl_v2_1/4/50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
993
  open-ed/A401_results/qwen3/sft_4B_cl_v2_1/4/75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
994
+ span_v3/ace_0_0.6B_cl/0/17/tokenizer.json filter=lfs diff=lfs merge=lfs -text
995
+ span_v3/ace_0_0.6B_cl/0/34/tokenizer.json filter=lfs diff=lfs merge=lfs -text
996
+ span_v3/ace_0_0.6B_cl/0/51/tokenizer.json filter=lfs diff=lfs merge=lfs -text
997
+ span_v3/ace_0_0.6B_cl/1/26/tokenizer.json filter=lfs diff=lfs merge=lfs -text
998
+ span_v3/ace_0_0.6B_cl/1/52/tokenizer.json filter=lfs diff=lfs merge=lfs -text
999
+ span_v3/ace_0_0.6B_cl/1/78/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1000
+ span_v3/ace_0_0.6B_cl/2/126/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1001
+ span_v3/ace_0_0.6B_cl/2/42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1002
+ span_v3/ace_0_0.6B_cl/2/84/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1003
+ span_v3/ace_0_0.6B_cl/3/27/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1004
+ span_v3/ace_0_0.6B_cl/3/54/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1005
+ span_v3/ace_0_0.6B_cl/3/81/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1006
+ span_v3/ace_0_0.6B_cl/4/25/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1007
+ span_v3/ace_0_0.6B_cl/4/50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1008
+ span_v3/ace_0_0.6B_cl/4/75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1009
+ span_v3/ace_1_0.6B_cl/0/17/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1010
+ span_v3/ace_1_0.6B_cl/0/34/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1011
+ span_v3/ace_1_0.6B_cl/0/51/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1012
+ span_v3/ace_1_0.6B_cl/1/22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1013
+ span_v3/ace_1_0.6B_cl/1/44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1014
+ span_v3/ace_1_0.6B_cl/1/66/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1015
+ span_v3/ace_1_0.6B_cl/2/120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1016
+ span_v3/ace_1_0.6B_cl/2/40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1017
+ span_v3/ace_1_0.6B_cl/2/80/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1018
+ span_v3/ace_1_0.6B_cl/3/29/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1019
+ span_v3/ace_1_0.6B_cl/3/58/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1020
+ span_v3/ace_1_0.6B_cl/3/87/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1021
+ span_v3/ace_1_0.6B_cl/4/25/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1022
+ span_v3/ace_1_0.6B_cl/4/50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1023
+ span_v3/ace_1_0.6B_cl/4/75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1024
+ span_v3/ace_2_0.6B_cl/0/17/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1025
+ span_v3/ace_2_0.6B_cl/0/34/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1026
+ span_v3/ace_2_0.6B_cl/0/51/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1027
+ span_v3/ace_2_0.6B_cl/1/23/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1028
+ span_v3/ace_2_0.6B_cl/1/46/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1029
+ span_v3/ace_2_0.6B_cl/1/69/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1030
+ span_v3/ace_2_0.6B_cl/2/28/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1031
+ span_v3/ace_2_0.6B_cl/2/56/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1032
+ span_v3/ace_2_0.6B_cl/2/84/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1033
+ span_v3/ace_2_0.6B_cl/3/24/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1034
+ span_v3/ace_2_0.6B_cl/3/48/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1035
+ span_v3/ace_2_0.6B_cl/3/72/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1036
+ span_v3/ace_2_0.6B_cl/4/135/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1037
+ span_v3/ace_2_0.6B_cl/4/45/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1038
+ span_v3/ace_2_0.6B_cl/4/90/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1039
+ span_v3/ace_3_0.6B_cl/0/23/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1040
+ span_v3/ace_3_0.6B_cl/0/46/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1041
+ span_v3/ace_3_0.6B_cl/0/69/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1042
+ span_v3/ace_3_0.6B_cl/1/114/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1043
+ span_v3/ace_3_0.6B_cl/1/38/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1044
+ span_v3/ace_3_0.6B_cl/1/76/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1045
+ span_v3/ace_3_0.6B_cl/2/21/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1046
+ span_v3/ace_3_0.6B_cl/2/42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1047
+ span_v3/ace_3_0.6B_cl/2/63/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1048
+ span_v3/ace_3_0.6B_cl/3/27/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1049
+ span_v3/ace_3_0.6B_cl/3/54/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1050
+ span_v3/ace_3_0.6B_cl/3/81/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1051
+ span_v3/ace_3_0.6B_cl/4/25/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1052
+ span_v3/ace_3_0.6B_cl/4/50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1053
+ span_v3/ace_3_0.6B_cl/4/75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1054
+ span_v3/ace_4_0.6B_cl/0/19/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1055
+ span_v3/ace_4_0.6B_cl/0/38/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1056
+ span_v3/ace_4_0.6B_cl/0/57/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1057
+ span_v3/ace_4_0.6B_cl/1/18/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1058
+ span_v3/ace_4_0.6B_cl/1/36/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1059
+ span_v3/ace_4_0.6B_cl/1/54/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1060
+ span_v3/ace_4_0.6B_cl/2/21/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1061
+ span_v3/ace_4_0.6B_cl/2/42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1062
+ span_v3/ace_4_0.6B_cl/2/63/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1063
+ span_v3/ace_4_0.6B_cl/3/30/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1064
+ span_v3/ace_4_0.6B_cl/3/60/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1065
+ span_v3/ace_4_0.6B_cl/3/90/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1066
+ span_v3/ace_4_0.6B_cl/4/135/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1067
+ span_v3/ace_4_0.6B_cl/4/45/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1068
+ span_v3/ace_4_0.6B_cl/4/90/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1069
+ span_v3/geneva_0_0.6B_cl/0/22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1070
+ span_v3/geneva_0_0.6B_cl/0/44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1071
+ span_v3/geneva_0_0.6B_cl/0/66/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1072
+ span_v3/geneva_0_0.6B_cl/1/28/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1073
+ span_v3/geneva_0_0.6B_cl/1/56/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1074
+ span_v3/geneva_0_0.6B_cl/1/84/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1075
+ span_v3/geneva_0_0.6B_cl/2/102/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1076
+ span_v3/geneva_0_0.6B_cl/2/34/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1077
+ span_v3/geneva_0_0.6B_cl/2/68/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1078
+ span_v3/geneva_0_0.6B_cl/3/120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1079
+ span_v3/geneva_0_0.6B_cl/3/40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1080
+ span_v3/geneva_0_0.6B_cl/3/80/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1081
+ span_v3/geneva_0_0.6B_cl/4/141/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1082
+ span_v3/geneva_0_0.6B_cl/4/47/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1083
+ span_v3/geneva_0_0.6B_cl/4/94/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1084
+ span_v3/geneva_1_0.6B_cl/0/20/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1085
+ span_v3/geneva_1_0.6B_cl/0/40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1086
+ span_v3/geneva_1_0.6B_cl/0/60/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1087
+ span_v3/geneva_1_0.6B_cl/1/25/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1088
+ span_v3/geneva_1_0.6B_cl/1/50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1089
+ span_v3/geneva_1_0.6B_cl/1/75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1090
+ span_v3/geneva_1_0.6B_cl/2/33/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1091
+ span_v3/geneva_1_0.6B_cl/2/66/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1092
+ span_v3/geneva_1_0.6B_cl/2/99/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1093
+ span_v3/geneva_1_0.6B_cl/3/123/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1094
+ span_v3/geneva_1_0.6B_cl/3/41/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1095
+ span_v3/geneva_1_0.6B_cl/3/82/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1096
+ span_v3/geneva_1_0.6B_cl/4/141/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1097
+ span_v3/geneva_1_0.6B_cl/4/47/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1098
+ span_v3/geneva_1_0.6B_cl/4/94/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1099
+ span_v3/geneva_2_0.6B_cl/0/22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1100
+ span_v3/geneva_2_0.6B_cl/0/44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1101
+ span_v3/geneva_2_0.6B_cl/0/66/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1102
+ span_v3/geneva_2_0.6B_cl/1/27/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1103
+ span_v3/geneva_2_0.6B_cl/1/54/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1104
+ span_v3/geneva_2_0.6B_cl/1/81/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1105
+ span_v3/geneva_2_0.6B_cl/2/105/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1106
+ span_v3/geneva_2_0.6B_cl/2/35/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1107
+ span_v3/geneva_2_0.6B_cl/2/70/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1108
+ span_v3/geneva_2_0.6B_cl/3/117/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1109
+ span_v3/geneva_2_0.6B_cl/3/39/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1110
+ span_v3/geneva_2_0.6B_cl/3/78/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1111
+ span_v3/geneva_2_0.6B_cl/4/138/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1112
+ span_v3/geneva_2_0.6B_cl/4/46/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1113
+ span_v3/geneva_2_0.6B_cl/4/92/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1114
+ span_v3/geneva_3_0.6B_cl/0/22/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1115
+ span_v3/geneva_3_0.6B_cl/0/44/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1116
+ span_v3/geneva_3_0.6B_cl/0/66/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1117
+ span_v3/geneva_3_0.6B_cl/1/28/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1118
+ span_v3/geneva_3_0.6B_cl/1/56/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1119
+ span_v3/geneva_3_0.6B_cl/1/84/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1120
+ span_v3/geneva_3_0.6B_cl/2/108/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1121
+ span_v3/geneva_3_0.6B_cl/2/36/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1122
+ span_v3/geneva_3_0.6B_cl/2/72/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1123
+ span_v3/geneva_3_0.6B_cl/3/120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1124
+ span_v3/geneva_3_0.6B_cl/3/40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1125
+ span_v3/geneva_3_0.6B_cl/3/80/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1126
+ span_v3/geneva_3_0.6B_cl/4/141/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1127
+ span_v3/geneva_3_0.6B_cl/4/47/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1128
+ span_v3/geneva_3_0.6B_cl/4/94/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1129
+ span_v3/geneva_4_0.6B_cl/0/20/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1130
+ span_v3/geneva_4_0.6B_cl/0/40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1131
+ span_v3/geneva_4_0.6B_cl/0/60/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1132
+ span_v3/geneva_4_0.6B_cl/1/27/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1133
+ span_v3/geneva_4_0.6B_cl/1/54/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1134
+ span_v3/geneva_4_0.6B_cl/1/81/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1135
+ span_v3/geneva_4_0.6B_cl/2/102/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1136
+ span_v3/geneva_4_0.6B_cl/2/34/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1137
+ span_v3/geneva_4_0.6B_cl/2/68/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1138
+ span_v3/geneva_4_0.6B_cl/3/120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1139
+ span_v3/geneva_4_0.6B_cl/3/40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1140
+ span_v3/geneva_4_0.6B_cl/3/80/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1141
+ span_v3/geneva_4_0.6B_cl/4/138/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1142
+ span_v3/geneva_4_0.6B_cl/4/46/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1143
+ span_v3/geneva_4_0.6B_cl/4/92/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1144
+ span_v3/maven_0_0.6B_cl/0/324/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1145
+ span_v3/maven_0_0.6B_cl/0/648/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1146
+ span_v3/maven_0_0.6B_cl/0/972/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1147
+ span_v3/maven_0_0.6B_cl/1/1038/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1148
+ span_v3/maven_0_0.6B_cl/1/346/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1149
+ span_v3/maven_0_0.6B_cl/1/692/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1150
+ span_v3/maven_0_0.6B_cl/2/1080/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1151
+ span_v3/maven_0_0.6B_cl/2/360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1152
+ span_v3/maven_0_0.6B_cl/2/720/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1153
+ span_v3/maven_0_0.6B_cl/3/334/tokenizer.json filter=lfs diff=lfs merge=lfs -text
span_v3/ace_0_0.6B_cl/0/17/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen3-0.6B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen3-0.6B
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.18.1
span_v3/ace_0_0.6B_cl/0/17/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3-0.6B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 128,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.1,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.1",
27
+ "qalora_group_size": 16,
28
+ "r": 64,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "k_proj",
33
+ "gate_proj",
34
+ "up_proj",
35
+ "o_proj",
36
+ "down_proj",
37
+ "v_proj",
38
+ "q_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
span_v3/ace_0_0.6B_cl/0/17/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:521034c05e4ce63db28afcd02697f23aa7ae517bf30c80ae79af38f27d12265c
3
+ size 80802963
span_v3/ace_0_0.6B_cl/0/17/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
span_v3/ace_0_0.6B_cl/0/17/chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
span_v3/ace_0_0.6B_cl/0/17/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
span_v3/ace_0_0.6B_cl/0/17/special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": "<|im_end|>",
18
+ "pad_token": "<|im_end|>"
19
+ }
span_v3/ace_0_0.6B_cl/0/17/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21f8fb0ec91ff3cb1156d458eb9363ebe8cf7a737ce8cb7f9d01dd5425c9870
3
+ size 11422929
span_v3/ace_0_0.6B_cl/0/17/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|im_end|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
span_v3/ace_0_0.6B_cl/0/17/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
span_v3/ace_0_0.6B_cl/0/34/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen3-0.6B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen3-0.6B
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.18.1
span_v3/ace_0_0.6B_cl/0/34/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3-0.6B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 128,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.1,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.1",
27
+ "qalora_group_size": 16,
28
+ "r": 64,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "k_proj",
33
+ "gate_proj",
34
+ "up_proj",
35
+ "o_proj",
36
+ "down_proj",
37
+ "v_proj",
38
+ "q_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
span_v3/ace_0_0.6B_cl/0/34/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7f9a03f334b6c19a21b79a6098f9c5ede449d835ad86555790956cba068eba2
3
+ size 80802963
span_v3/ace_0_0.6B_cl/0/34/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
span_v3/ace_0_0.6B_cl/0/34/chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
span_v3/ace_0_0.6B_cl/0/34/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
span_v3/ace_0_0.6B_cl/0/34/special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": "<|im_end|>",
18
+ "pad_token": "<|im_end|>"
19
+ }
span_v3/ace_0_0.6B_cl/0/34/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21f8fb0ec91ff3cb1156d458eb9363ebe8cf7a737ce8cb7f9d01dd5425c9870
3
+ size 11422929
span_v3/ace_0_0.6B_cl/0/34/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|im_end|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
span_v3/ace_0_0.6B_cl/0/34/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
span_v3/ace_0_0.6B_cl/0/51/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen3-0.6B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen3-0.6B
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.18.1
span_v3/ace_0_0.6B_cl/0/51/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3-0.6B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 128,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.1,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.1",
27
+ "qalora_group_size": 16,
28
+ "r": 64,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "k_proj",
33
+ "gate_proj",
34
+ "up_proj",
35
+ "o_proj",
36
+ "down_proj",
37
+ "v_proj",
38
+ "q_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
span_v3/ace_0_0.6B_cl/0/51/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e48c2acea925c6fa3808a0055dd0e5be6c86c39ac5e0a3963622efc259195c3c
3
+ size 80802963
span_v3/ace_0_0.6B_cl/0/51/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
span_v3/ace_0_0.6B_cl/0/51/chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
span_v3/ace_0_0.6B_cl/0/51/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
span_v3/ace_0_0.6B_cl/0/51/special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": "<|im_end|>",
18
+ "pad_token": "<|im_end|>"
19
+ }
span_v3/ace_0_0.6B_cl/0/51/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21f8fb0ec91ff3cb1156d458eb9363ebe8cf7a737ce8cb7f9d01dd5425c9870
3
+ size 11422929
span_v3/ace_0_0.6B_cl/0/51/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|im_end|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
span_v3/ace_0_0.6B_cl/0/51/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
span_v3/ace_0_0.6B_cl/0/args.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_path": "Qwen/Qwen3-0.6B", "ckpt_name": "qwen3-0.6B", "model_type": "qwen", "teacher_model_type": null, "n_gpu": 2, "n_nodes": 1, "teacher_model_path": null, "teacher_ckpt_name": null, "teacher_model_fp16": false, "model_parallel": false, "model_parallel_size": null, "no_value": false, "dropout_path_rate": null, "fp32": false, "bf16": false, "type": "fkl", "do_train": true, "do_valid": true, "do_eval": true, "base_path": ".", "load": null, "save": "./results/qwen3/span_v3/ace_0_0.6B_cl/0", "log_interval": 10, "mid_log_num": -1, "save_interval": -1, "eval_interval": -1, "local_rank": 0, "save_additional_suffix": "", "save_rollout": false, "eb_sample_times": 3, "data_dir": "./processed_data/ace_v3_0/0/qwen/", "processed_data_dir": null, "force_process": false, "force_process_demo": false, "data_process_workers": -1, "train_num": -1, "train_ratio": 1, "dev_num": -1, "dev_ratio": 1, "gen_num": -1, "data_names": null, "prompt_type": null, "num_workers": 0, "max_prompt_length": 512, "t_max_prompt_length": 768, "min_prompt_length": 128, "json_data": false, "bin_data": false, "txt_data": false, "prompt_data_dir": null, "lm_data_dir": null, "eval_ppl": false, "eval_rw": false, "eval_gen": true, "only_prompt": false, "batch_size": 4, "eval_batch_size": 32, "clip_grad": 1.0, "total_iters": null, "train_iters_per_epoch": -1, "max_length": 640, "t_max_length": 768, "seed": 42, "seed_order": 42, "seed_data": 42, "seed_ppo": 42, "seed_lm": 7, "epochs": 3, "training_epochs": 10000, "gradient_accumulation_steps": 4, "gradient_checkpointing": false, "attn_dtype": null, "lr": 0.0001, "lr_min": 1e-07, "weight_decay": 0.01, "loss_scale": 65536, "kd_ratio": 0.3, "cl_task_id": 0, "cl_distill_coef": 0.5, "warmup_iters": 0, "warmup_ratio": 0.1, "lr_decay_iters": null, "lr_decay_style": "wrmup_cosine", "scheduler_name": "constant_trm", "w_span_loss": 1.0, "reward_scaling": null, "cliprange_reward": 1, "ppo_epochs": null, "num_rollouts": 256, "num_rollouts_per_device": null, "cliprange": 0.2, "chunk_size": null, "gamma": 0.95, "length_norm": false, "single_step_reg": false, "teacher_mixed_alpha": null, "lm_coef": 1, "skew_alpha": 0.1, "student_gen": false, "gen_top_p": 1.0, "gen_num_beams": 2, "mixed_alpha": 0.5, "loss_eps": 0.1, "init_threshold": 0.0, "student_layer_mapping": [22, 25, 28], "teacher_layer_mapping": [22, 25, 28], "split_layer_mapping": [0, 0, 0, 0], "use_dsa": false, "use_hs": false, "top_k": 0, "top_p": 0.95, "do_sample": true, "no_repeat_ngram_size": 6, "repetition_penalty": null, "num_beams": 1, "temperature": 0.5, "peft": "lora", "peft_lora_r": 64, "peft_lora_alpha": 128, "peft_lora_dropout": 0.1, "peft_name": null, "peft_path": null, "teacher_peft_name": null, "teacher_peft_path": null, "deepspeed": true, "deepspeed_config": "./configs/deepspeed/ds_config_bf16.json", "deepscale": false, "deepscale_config": null, "rank": 0, "world_size": 2}
span_v3/ace_0_0.6B_cl/0/eval/0/answers.jsonl ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"text": "{\"events\": [[\"named\", \"Personnel:Nominate\"]]}"}
2
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
3
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
4
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
5
+ {"text": "{\"events\": [[\"formed\", \"Business:Start-Org\"]]}"}
6
+ {"text": "{\"events\": [[\"forum\", \"Contact:Meet\"]]}"}
7
+ {"text": "{\"events\": [[\"Negotiations\", \"Contact:Meet\"], [\"meeting\", \"Contact:Meet\"]]}"}
8
+ {"text": "{\"events\": [[\"meet\", \"Contact:Meet\"]]}"}
9
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
10
+ {"text": "{\"events\": [[\"conviction\", \"Justice:Convict\"]]}"}
11
+ {"text": "{\"events\": [[\"trials\", \"Justice:Trial-Hearing\"]]}"}
12
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
13
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
14
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
15
+ {"text": "{\"events\": [[\"brief\", \"Contact:Meet\"]]}"}
16
+ {"text": "{\"events\": [[\"conviction\", \"Justice:Convict\"]]}"}
17
+ {"text": "{\"events\": [[\"guilty\", \"Justice:Convict\"]]}"}
18
+ {"text": "{\"events\": [[\"convicted\", \"Justice:Convict\"]]}"}
19
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
20
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
21
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
22
+ {"text": "{\"events\": [[\"discussions\", \"Contact:Meet\"]]}"}
23
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
24
+ {"text": "{\"events\": [[\"founded\", \"Business:Start-Org\"]]}"}
25
+ {"text": "{\"events\": [[\"create\", \"Business:Start-Org\"]]}"}
26
+ {"text": "{\"events\": [[\"forging\", \"Contact:Meet\"]]}"}
27
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
28
+ {"text": "{\"events\": [[\"launching\", \"Business:Start-Org\"], [\"opening\", \"Business:Start-Org\"]]}"}
29
+ {"text": "{\"events\": [[\"build\", \"Business:Start-Org\"]]}"}
30
+ {"text": "{\"events\": [[\"create\", \"Business:Start-Org\"]]}"}
31
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
32
+ {"text": "{\"events\": [[\"founded\", \"Business:Start-Org\"]]}"}
33
+ {"text": "{\"events\": [[\"elected\", \"Personnel:Elect\"]]}"}
34
+ {"text": "{\"events\": [[\"election\", \"Personnel:Elect\"]]}"}
35
+ {"text": "{\"events\": [[\"Founded\", \"Business:Start-Org\"]]}"}
36
+ {"text": "{\"events\": [[\"creating\", \"Business:Start-Org\"]]}"}
37
+ {"text": "{\"events\": [[\"hearing\", \"Justice:Trial-Hearing\"]]}"}
38
+ {"text": "{\"events\": [[\"conviction\", \"Justice:Convict\"]]}"}
39
+ {"text": "{\"events\": [[\"convicted\", \"Justice:Convict\"]]}"}
40
+ {"text": "{\"events\": [[\"launched\", \"Business:Start-Org\"]]}"}
41
+ {"text": "{\"events\": [[\"debut\", \"Business:Start-Org\"], [\"open\", \"Business:Start-Org\"]]}"}
42
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
43
+ {"text": "{\"events\": [[\"discussed\", \"Contact:Meet\"]]}"}
44
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
45
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
46
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
47
+ {"text": "{\"events\": [[\"met\", \"Contact:Meet\"]]}"}
48
+ {"text": "{\"events\": [[\"elected\", \"Personnel:Elect\"]]}"}
49
+ {"text": "{\"events\": [[\"elected\", \"Personnel:Elect\"]]}"}
50
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
51
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
52
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
53
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
54
+ {"text": "{\"events\": [[\"meet\", \"Contact:Meet\"]]}"}
55
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
56
+ {"text": "{\"events\": [[\"discussions\", \"Contact:Meet\"]]}"}
57
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
58
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
59
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"], [\"summit\", \"Contact:Meet\"]]}"}
60
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
61
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
62
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
63
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
64
+ {"text": "{\"events\": [[\"inviting\", \"Contact:Meet\"]]}"}
65
+ {"text": "{\"events\": [[\"visited\", \"Contact:Meet\"]]}"}
66
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
67
+ {"text": "{\"events\": [[\"met\", \"Contact:Meet\"]]}"}
68
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"], [\"summit\", \"Contact:Meet\"]]}"}
69
+ {"text": "{\"events\": [[\"birth\", \"Life:Be-Born\"]]}"}
70
+ {"text": "{\"events\": [[\"born\", \"Life:Be-Born\"]]}"}
71
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
72
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
73
+ {"text": "{\"events\": [[\"born\", \"Life:Be-Born\"]]}"}
74
+ {"text": "{\"events\": [[\"create\", \"Business:Start-Org\"]]}"}
75
+ {"text": "{\"events\": [[\"war\", \"Contact:Meet\"]]}"}
76
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
77
+ {"text": "{\"events\": [[\"trial\", \"Justice:Trial-Hearing\"]]}"}
78
+ {"text": "{\"events\": [[\"tried\", \"Justice:Trial-Hearing\"]]}"}
79
+ {"text": "{\"events\": [[\"trial\", \"Justice:Trial-Hearing\"]]}"}
80
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
81
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
82
+ {"text": "{\"events\": [[\"named\", \"Personnel:Nominate\"]]}"}
83
+ {"text": "{\"events\": [[\"elected\", \"Personnel:Elect\"]]}"}
84
+ {"text": "{\"events\": [[\"won\", \"Personnel:Elect\"]]}"}
85
+ {"text": "{\"events\": [[\"met\", \"Contact:Meet\"]]}"}
86
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
87
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
88
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
89
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
90
+ {"text": "{\"events\": [[\"met\", \"Contact:Meet\"]]}"}
91
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
92
+ {"text": "{\"events\": [[\"launch\", \"Business:Start-Org\"]]}"}
93
+ {"text": "{\"events\": [[\"creating\", \"Business:Start-Org\"]]}"}
94
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
95
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
96
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
97
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
98
+ {"text": "{\"events\": [[\"breakdowns\", \"Life:Be-Born\"]]}"}
span_v3/ace_0_0.6B_cl/0/eval/1/answers.jsonl ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"text": "{\"events\": [[\"named\", \"Personnel:Nominate\"]]}"}
2
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
3
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
4
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
5
+ {"text": "{\"events\": [[\"formed\", \"Business:Start-Org\"]]}"}
6
+ {"text": "{\"events\": [[\"forum\", \"Contact:Meet\"]]}"}
7
+ {"text": "{\"events\": [[\"Negotiations\", \"Contact:Meet\"], [\"meeting\", \"Contact:Meet\"]]}"}
8
+ {"text": "{\"events\": [[\"meet\", \"Contact:Meet\"]]}"}
9
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
10
+ {"text": "{\"events\": [[\"conviction\", \"Justice:Convict\"]]}"}
11
+ {"text": "{\"events\": [[\"trials\", \"Justice:Trial-Hearing\"]]}"}
12
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
13
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
14
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
15
+ {"text": "{\"events\": [[\"brief\", \"Contact:Meet\"]]}"}
16
+ {"text": "{\"events\": [[\"conviction\", \"Justice:Convict\"]]}"}
17
+ {"text": "{\"events\": [[\"guilty\", \"Justice:Convict\"]]}"}
18
+ {"text": "{\"events\": [[\"convicted\", \"Justice:Convict\"]]}"}
19
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
20
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
21
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
22
+ {"text": "{\"events\": [[\"discussions\", \"Contact:Meet\"]]}"}
23
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
24
+ {"text": "{\"events\": [[\"founded\", \"Business:Start-Org\"]]}"}
25
+ {"text": "{\"events\": [[\"create\", \"Business:Start-Org\"]]}"}
26
+ {"text": "{\"events\": [[\"forging\", \"Business:Start-Org\"]]}"}
27
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
28
+ {"text": "{\"events\": [[\"launching\", \"Business:Start-Org\"], [\"opening\", \"Business:Start-Org\"]]}"}
29
+ {"text": "{\"events\": [[\"build\", \"Business:Start-Org\"]]}"}
30
+ {"text": "{\"events\": [[\"create\", \"Business:Start-Org\"]]}"}
31
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
32
+ {"text": "{\"events\": [[\"founded\", \"Business:Start-Org\"]]}"}
33
+ {"text": "{\"events\": [[\"elected\", \"Personnel:Elect\"]]}"}
34
+ {"text": "{\"events\": [[\"election\", \"Personnel:Elect\"]]}"}
35
+ {"text": "{\"events\": [[\"Founded\", \"Business:Start-Org\"]]}"}
36
+ {"text": "{\"events\": [[\"creating\", \"Business:Start-Org\"]]}"}
37
+ {"text": "{\"events\": [[\"hearing\", \"Justice:Trial-Hearing\"]]}"}
38
+ {"text": "{\"events\": [[\"conviction\", \"Justice:Convict\"]]}"}
39
+ {"text": "{\"events\": [[\"convicted\", \"Justice:Convict\"]]}"}
40
+ {"text": "{\"events\": [[\"launched\", \"Business:Start-Org\"]]}"}
41
+ {"text": "{\"events\": [[\"debut\", \"Business:Start-Org\"], [\"open\", \"Business:Start-Org\"]]}"}
42
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
43
+ {"text": "{\"events\": [[\"discussed\", \"Contact:Meet\"]]}"}
44
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
45
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
46
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
47
+ {"text": "{\"events\": [[\"met\", \"Contact:Meet\"]]}"}
48
+ {"text": "{\"events\": [[\"elected\", \"Personnel:Elect\"]]}"}
49
+ {"text": "{\"events\": [[\"elected\", \"Personnel:Elect\"]]}"}
50
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
51
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
52
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
53
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
54
+ {"text": "{\"events\": [[\"meet\", \"Contact:Meet\"]]}"}
55
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
56
+ {"text": "{\"events\": [[\"discussions\", \"Contact:Meet\"]]}"}
57
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
58
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
59
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"], [\"summit\", \"Contact:Meet\"]]}"}
60
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
61
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
62
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
63
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
64
+ {"text": "{\"events\": [[\"inviting\", \"Contact:Meet\"]]}"}
65
+ {"text": "{\"events\": [[\"visited\", \"Contact:Meet\"]]}"}
66
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
67
+ {"text": "{\"events\": [[\"met\", \"Contact:Meet\"]]}"}
68
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"], [\"summit\", \"Contact:Meet\"]]}"}
69
+ {"text": "{\"events\": [[\"birth\", \"Life:Be-Born\"]]}"}
70
+ {"text": "{\"events\": [[\"born\", \"Life:Be-Born\"]]}"}
71
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
72
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
73
+ {"text": "{\"events\": [[\"born\", \"Life:Be-Born\"]]}"}
74
+ {"text": "{\"events\": [[\"create\", \"Business:Start-Org\"]]}"}
75
+ {"text": "{\"events\": [[\"war\", \"Contact:Meet\"]]}"}
76
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
77
+ {"text": "{\"events\": [[\"trial\", \"Justice:Trial-Hearing\"]]}"}
78
+ {"text": "{\"events\": [[\"tried\", \"Justice:Trial-Hearing\"]]}"}
79
+ {"text": "{\"events\": [[\"trial\", \"Justice:Trial-Hearing\"]]}"}
80
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
81
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
82
+ {"text": "{\"events\": [[\"named\", \"Personnel:Nominate\"]]}"}
83
+ {"text": "{\"events\": [[\"elected\", \"Personnel:Elect\"]]}"}
84
+ {"text": "{\"events\": [[\"won\", \"Personnel:Elect\"]]}"}
85
+ {"text": "{\"events\": [[\"met\", \"Contact:Meet\"]]}"}
86
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
87
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
88
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
89
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
90
+ {"text": "{\"events\": [[\"met\", \"Contact:Meet\"]]}"}
91
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
92
+ {"text": "{\"events\": [[\"launch\", \"Business:Start-Org\"]]}"}
93
+ {"text": "{\"events\": [[\"creating\", \"Business:Start-Org\"]]}"}
94
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
95
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
96
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
97
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
98
+ {"text": "{\"events\": [[\"breakdowns\", \"Life:Divorce\"]]}"}
span_v3/ace_0_0.6B_cl/0/eval/2/answers.jsonl ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"text": "{\"events\": [[\"named\", \"Personnel:Nominate\"]]}"}
2
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
3
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
4
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
5
+ {"text": "{\"events\": [[\"formed\", \"Business:Start-Org\"]]}"}
6
+ {"text": "{\"events\": [[\"forum\", \"Contact:Meet\"]]}"}
7
+ {"text": "{\"events\": [[\"Negotiations\", \"Contact:Meet\"], [\"meeting\", \"Contact:Meet\"]]}"}
8
+ {"text": "{\"events\": [[\"meet\", \"Contact:Meet\"]]}"}
9
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
10
+ {"text": "{\"events\": [[\"conviction\", \"Justice:Convict\"]]}"}
11
+ {"text": "{\"events\": [[\"trials\", \"Justice:Trial-Hearing\"]]}"}
12
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
13
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
14
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
15
+ {"text": "{\"events\": [[\"brief\", \"Contact:Meet\"]]}"}
16
+ {"text": "{\"events\": [[\"conviction\", \"Justice:Convict\"]]}"}
17
+ {"text": "{\"events\": [[\"guilty\", \"Justice:Convict\"]]}"}
18
+ {"text": "{\"events\": [[\"convicted\", \"Justice:Convict\"]]}"}
19
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
20
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
21
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
22
+ {"text": "{\"events\": [[\"discussions\", \"Contact:Meet\"]]}"}
23
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
24
+ {"text": "{\"events\": [[\"founded\", \"Business:Start-Org\"]]}"}
25
+ {"text": "{\"events\": [[\"create\", \"Business:Start-Org\"]]}"}
26
+ {"text": "{\"events\": [[\"forging\", \"Contact:Meet\"]]}"}
27
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
28
+ {"text": "{\"events\": [[\"launching\", \"Business:Start-Org\"], [\"opening\", \"Business:Start-Org\"]]}"}
29
+ {"text": "{\"events\": [[\"build\", \"Business:Start-Org\"]]}"}
30
+ {"text": "{\"events\": [[\"create\", \"Business:Start-Org\"]]}"}
31
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
32
+ {"text": "{\"events\": [[\"founded\", \"Business:Start-Org\"]]}"}
33
+ {"text": "{\"events\": [[\"elected\", \"Personnel:Elect\"]]}"}
34
+ {"text": "{\"events\": [[\"election\", \"Personnel:Elect\"]]}"}
35
+ {"text": "{\"events\": [[\"Founded\", \"Business:Start-Org\"]]}"}
36
+ {"text": "{\"events\": [[\"creating\", \"Business:Start-Org\"]]}"}
37
+ {"text": "{\"events\": [[\"hearing\", \"Justice:Trial-Hearing\"]]}"}
38
+ {"text": "{\"events\": [[\"conviction\", \"Justice:Convict\"]]}"}
39
+ {"text": "{\"events\": [[\"convicted\", \"Justice:Convict\"]]}"}
40
+ {"text": "{\"events\": [[\"launched\", \"Business:Start-Org\"]]}"}
41
+ {"text": "{\"events\": [[\"debut\", \"Business:Start-Org\"], [\"open\", \"Business:Start-Org\"]]}"}
42
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
43
+ {"text": "{\"events\": [[\"discussed\", \"Contact:Meet\"]]}"}
44
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
45
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
46
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
47
+ {"text": "{\"events\": [[\"met\", \"Contact:Meet\"]]}"}
48
+ {"text": "{\"events\": [[\"elected\", \"Personnel:Elect\"]]}"}
49
+ {"text": "{\"events\": [[\"elected\", \"Personnel:Elect\"]]}"}
50
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
51
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
52
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
53
+ {"text": "{\"events\": [[\"elections\", \"Personnel:Elect\"]]}"}
54
+ {"text": "{\"events\": [[\"meet\", \"Contact:Meet\"]]}"}
55
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
56
+ {"text": "{\"events\": [[\"discussions\", \"Contact:Meet\"]]}"}
57
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
58
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
59
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"], [\"summit\", \"Contact:Meet\"]]}"}
60
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
61
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
62
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
63
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
64
+ {"text": "{\"events\": [[\"inviting\", \"Contact:Meet\"]]}"}
65
+ {"text": "{\"events\": [[\"visited\", \"Contact:Meet\"]]}"}
66
+ {"text": "{\"events\": [[\"summit\", \"Contact:Meet\"]]}"}
67
+ {"text": "{\"events\": [[\"met\", \"Contact:Meet\"]]}"}
68
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"], [\"summit\", \"Contact:Meet\"]]}"}
69
+ {"text": "{\"events\": [[\"birth\", \"Life:Be-Born\"]]}"}
70
+ {"text": "{\"events\": [[\"born\", \"Life:Be-Born\"]]}"}
71
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
72
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
73
+ {"text": "{\"events\": [[\"born\", \"Life:Be-Born\"]]}"}
74
+ {"text": "{\"events\": [[\"create\", \"Business:Start-Org\"]]}"}
75
+ {"text": "{\"events\": [[\"war\", \"Contact:Meet\"]]}"}
76
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
77
+ {"text": "{\"events\": [[\"trial\", \"Justice:Trial-Hearing\"]]}"}
78
+ {"text": "{\"events\": [[\"tried\", \"Justice:Trial-Hearing\"]]}"}
79
+ {"text": "{\"events\": [[\"trial\", \"Justice:Trial-Hearing\"]]}"}
80
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
81
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
82
+ {"text": "{\"events\": [[\"named\", \"Personnel:Nominate\"]]}"}
83
+ {"text": "{\"events\": [[\"elected\", \"Personnel:Elect\"]]}"}
84
+ {"text": "{\"events\": [[\"won\", \"Personnel:Elect\"]]}"}
85
+ {"text": "{\"events\": [[\"met\", \"Contact:Meet\"]]}"}
86
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
87
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
88
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
89
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
90
+ {"text": "{\"events\": [[\"met\", \"Contact:Meet\"]]}"}
91
+ {"text": "{\"events\": [[\"talks\", \"Contact:Meet\"]]}"}
92
+ {"text": "{\"events\": [[\"launch\", \"Business:Start-Org\"]]}"}
93
+ {"text": "{\"events\": [[\"creating\", \"Business:Start-Org\"]]}"}
94
+ {"text": "{\"events\": [[\"meeting\", \"Contact:Meet\"]]}"}
95
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
96
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
97
+ {"text": "{\"events\": [[\"divorce\", \"Life:Divorce\"]]}"}
98
+ {"text": "{\"events\": [[\"breakdowns\", \"Life:Divorce\"]]}"}
span_v3/ace_0_0.6B_cl/0/log.txt ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+
3
+ ============================== EXP at 2026-03-16 04:12:33 ==============================
4
+ dev | avg_loss: 2.84375 | {'exact_match': 0.0, 'rougeL': 50.3004, 'trigger_counts': {'tp': 0, 'fp': 29, 'fn': 40}, 'argument_counts': {'tp': 0, 'fp': 0, 'fn': 0}, 'trigger_text': {'precision': 0.6538461538461539, 'recall': 0.425, 'f1': 0.5151515151515152}, 'trigger': {'precision': 0.0, 'recall': 0.0, 'f1': 0}, 'argument': {'precision': 0, 'recall': 0, 'f1': 0}, 'trigger_per_type': {'contact:meet': {'counts': {'tp': 0, 'fp': 0, 'fn': 29}, 'precision': 0, 'recall': 0.0, 'f1': 0}, 'personnel:elect': {'counts': {'tp': 0, 'fp': 0, 'fn': 4}, 'precision': 0, 'recall': 0.0, 'f1': 0}, 'justice:convict': {'counts': {'tp': 0, 'fp': 0, 'fn': 6}, 'precision': 0, 'recall': 0.0, 'f1': 0}, 'justice:trial-hearing': {'counts': {'tp': 0, 'fp': 0, 'fn': 1}, 'precision': 0, 'recall': 0.0, 'f1': 0}}}
5
+ train | epoch 0 | Iter: 36/ 204 | global iter: 10/ 51 | loss: 1.3859 | ds_loss: 0.0000 | lr: 9.8229e-05 | scale: 1.0000 | micro time: 0.424 | step time: 1.497
6
+ dev | avg_loss: 0.00982666015625 | {'exact_match': 100.0, 'rougeL': 100.0, 'trigger_counts': {'tp': 40, 'fp': 0, 'fn': 0}, 'argument_counts': {'tp': 0, 'fp': 0, 'fn': 0}, 'trigger_text': {'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'trigger': {'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'argument': {'precision': 0, 'recall': 0, 'f1': 0}, 'trigger_per_type': {'contact:meet': {'counts': {'tp': 29, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'personnel:elect': {'counts': {'tp': 4, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'justice:convict': {'counts': {'tp': 6, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'justice:trial-hearing': {'counts': {'tp': 1, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}}}
7
+ test | avg_loss: 0.0262451171875 | {'exact_match': 95.9184, 'rougeL': 98.1179, 'trigger_counts': {'tp': 99, 'fp': 4, 'fn': 4}, 'argument_counts': {'tp': 0, 'fp': 0, 'fn': 0}, 'trigger_text': {'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'trigger': {'precision': 0.9611650485436893, 'recall': 0.9611650485436893, 'f1': 0.9611650485436893}, 'argument': {'precision': 0, 'recall': 0, 'f1': 0}, 'trigger_per_type': {'business:start-org': {'counts': {'tp': 15, 'fp': 1, 'fn': 2}, 'precision': 0.9375, 'recall': 0.8823529411764706, 'f1': 0.9090909090909091}, 'personnel:nominate': {'counts': {'tp': 0, 'fp': 0, 'fn': 1}, 'precision': 0, 'recall': 0.0, 'f1': 0}, 'contact:meet': {'counts': {'tp': 49, 'fp': 1, 'fn': 0}, 'precision': 0.98, 'recall': 1.0, 'f1': 0.98989898989899}, 'personnel:elect': {'counts': {'tp': 13, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'justice:convict': {'counts': {'tp': 6, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'justice:trial-hearing': {'counts': {'tp': 5, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'life:divorce': {'counts': {'tp': 8, 'fp': 0, 'fn': 1}, 'precision': 1.0, 'recall': 0.8888888888888888, 'f1': 0.9411764705882353}, 'life:be-born': {'counts': {'tp': 3, 'fp': 1, 'fn': 0}, 'precision': 0.75, 'recall': 1.0, 'f1': 0.8571428571428571}}}
8
+ train | epoch 1 | Iter: 76/ 204 | global iter: 20/ 51 | loss: 0.1034 | ds_loss: 0.0000 | lr: 7.9028e-05 | scale: 1.0000 | micro time: 0.425 | step time: 1.642
9
+ train | epoch 1 | Iter: 116/ 204 | global iter: 30/ 51 | loss: 0.0171 | ds_loss: 0.0000 | lr: 4.6751e-05 | scale: 1.0000 | micro time: 0.425 | step time: 1.654
10
+ dev | avg_loss: 0.00927734375 | {'exact_match': 97.3684, 'rougeL': 99.2823, 'trigger_counts': {'tp': 39, 'fp': 0, 'fn': 1}, 'argument_counts': {'tp': 0, 'fp': 0, 'fn': 0}, 'trigger_text': {'precision': 1.0, 'recall': 0.975, 'f1': 0.9873417721518987}, 'trigger': {'precision': 1.0, 'recall': 0.975, 'f1': 0.9873417721518987}, 'argument': {'precision': 0, 'recall': 0, 'f1': 0}, 'trigger_per_type': {'contact:meet': {'counts': {'tp': 28, 'fp': 0, 'fn': 1}, 'precision': 1.0, 'recall': 0.9655172413793104, 'f1': 0.9824561403508771}, 'personnel:elect': {'counts': {'tp': 4, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'justice:convict': {'counts': {'tp': 6, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'justice:trial-hearing': {'counts': {'tp': 1, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}}}
11
+ test | avg_loss: 0.00513458251953125 | {'exact_match': 98.9796, 'rougeL': 99.7449, 'trigger_counts': {'tp': 102, 'fp': 1, 'fn': 1}, 'argument_counts': {'tp': 0, 'fp': 0, 'fn': 0}, 'trigger_text': {'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'trigger': {'precision': 0.9902912621359223, 'recall': 0.9902912621359223, 'f1': 0.9902912621359223}, 'argument': {'precision': 0, 'recall': 0, 'f1': 0}, 'trigger_per_type': {'personnel:nominate': {'counts': {'tp': 1, 'fp': 1, 'fn': 0}, 'precision': 0.5, 'recall': 1.0, 'f1': 0.6666666666666666}, 'contact:meet': {'counts': {'tp': 49, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'business:start-org': {'counts': {'tp': 17, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'personnel:elect': {'counts': {'tp': 12, 'fp': 0, 'fn': 1}, 'precision': 1.0, 'recall': 0.9230769230769231, 'f1': 0.9600000000000001}, 'justice:convict': {'counts': {'tp': 6, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'justice:trial-hearing': {'counts': {'tp': 5, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'life:divorce': {'counts': {'tp': 9, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'life:be-born': {'counts': {'tp': 3, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}}}
12
+ train | epoch 2 | Iter: 156/ 204 | global iter: 40/ 51 | loss: 0.0052 | ds_loss: 0.0000 | lr: 1.5938e-05 | scale: 1.0000 | micro time: 0.425 | step time: 1.644
13
+ train | epoch 2 | Iter: 196/ 204 | global iter: 50/ 51 | loss: 0.0026 | ds_loss: 0.0000 | lr: 4.6773e-07 | scale: 1.0000 | micro time: 0.425 | step time: 1.655
14
+ dev | avg_loss: 0.0048828125 | {'exact_match': 97.3684, 'rougeL': 99.2823, 'trigger_counts': {'tp': 39, 'fp': 0, 'fn': 1}, 'argument_counts': {'tp': 0, 'fp': 0, 'fn': 0}, 'trigger_text': {'precision': 1.0, 'recall': 0.975, 'f1': 0.9873417721518987}, 'trigger': {'precision': 1.0, 'recall': 0.975, 'f1': 0.9873417721518987}, 'argument': {'precision': 0, 'recall': 0, 'f1': 0}, 'trigger_per_type': {'contact:meet': {'counts': {'tp': 28, 'fp': 0, 'fn': 1}, 'precision': 1.0, 'recall': 0.9655172413793104, 'f1': 0.9824561403508771}, 'personnel:elect': {'counts': {'tp': 4, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'justice:convict': {'counts': {'tp': 6, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'justice:trial-hearing': {'counts': {'tp': 1, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}}}
15
+ test | avg_loss: 0.00522613525390625 | {'exact_match': 97.9592, 'rougeL': 99.178, 'trigger_counts': {'tp': 101, 'fp': 2, 'fn': 2}, 'argument_counts': {'tp': 0, 'fp': 0, 'fn': 0}, 'trigger_text': {'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'trigger': {'precision': 0.9805825242718447, 'recall': 0.9805825242718447, 'f1': 0.9805825242718447}, 'argument': {'precision': 0, 'recall': 0, 'f1': 0}, 'trigger_per_type': {'personnel:nominate': {'counts': {'tp': 1, 'fp': 1, 'fn': 0}, 'precision': 0.5, 'recall': 1.0, 'f1': 0.6666666666666666}, 'contact:meet': {'counts': {'tp': 49, 'fp': 1, 'fn': 0}, 'precision': 0.98, 'recall': 1.0, 'f1': 0.98989898989899}, 'business:start-org': {'counts': {'tp': 16, 'fp': 0, 'fn': 1}, 'precision': 1.0, 'recall': 0.9411764705882353, 'f1': 0.9696969696969697}, 'personnel:elect': {'counts': {'tp': 12, 'fp': 0, 'fn': 1}, 'precision': 1.0, 'recall': 0.9230769230769231, 'f1': 0.9600000000000001}, 'justice:convict': {'counts': {'tp': 6, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'justice:trial-hearing': {'counts': {'tp': 5, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'life:divorce': {'counts': {'tp': 9, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'life:be-born': {'counts': {'tp': 3, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}}}
16
+ test | avg_loss: 0.00522613525390625 | {'exact_match': 96.9388, 'rougeL': 98.8379, 'trigger_counts': {'tp': 100, 'fp': 3, 'fn': 3}, 'argument_counts': {'tp': 0, 'fp': 0, 'fn': 0}, 'trigger_text': {'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'trigger': {'precision': 0.970873786407767, 'recall': 0.970873786407767, 'f1': 0.970873786407767}, 'argument': {'precision': 0, 'recall': 0, 'f1': 0}, 'trigger_per_type': {'personnel:nominate': {'counts': {'tp': 1, 'fp': 1, 'fn': 0}, 'precision': 0.5, 'recall': 1.0, 'f1': 0.6666666666666666}, 'contact:meet': {'counts': {'tp': 49, 'fp': 1, 'fn': 0}, 'precision': 0.98, 'recall': 1.0, 'f1': 0.98989898989899}, 'business:start-org': {'counts': {'tp': 16, 'fp': 0, 'fn': 1}, 'precision': 1.0, 'recall': 0.9411764705882353, 'f1': 0.9696969696969697}, 'personnel:elect': {'counts': {'tp': 12, 'fp': 0, 'fn': 1}, 'precision': 1.0, 'recall': 0.9230769230769231, 'f1': 0.9600000000000001}, 'justice:convict': {'counts': {'tp': 6, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'justice:trial-hearing': {'counts': {'tp': 5, 'fp': 0, 'fn': 0}, 'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'life:divorce': {'counts': {'tp': 8, 'fp': 0, 'fn': 1}, 'precision': 1.0, 'recall': 0.8888888888888888, 'f1': 0.9411764705882353}, 'life:be-born': {'counts': {'tp': 3, 'fp': 1, 'fn': 0}, 'precision': 0.75, 'recall': 1.0, 'f1': 0.8571428571428571}}}
span_v3/ace_0_0.6B_cl/1/26/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen3-0.6B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen3-0.6B
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.18.1
span_v3/ace_0_0.6B_cl/1/26/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3-0.6B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 128,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.1,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.1",
27
+ "qalora_group_size": 16,
28
+ "r": 64,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "o_proj",
33
+ "up_proj",
34
+ "gate_proj",
35
+ "down_proj",
36
+ "k_proj",
37
+ "q_proj",
38
+ "v_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
span_v3/ace_0_0.6B_cl/1/26/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd1defeabff971ede2264d59a2d154fd3fc05551de4f282da4ca5e4c42d29f19
3
+ size 80802963
span_v3/ace_0_0.6B_cl/1/26/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
span_v3/ace_0_0.6B_cl/1/26/chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
span_v3/ace_0_0.6B_cl/1/26/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
span_v3/ace_0_0.6B_cl/1/26/special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": "<|im_end|>",
18
+ "pad_token": "<|im_end|>"
19
+ }
span_v3/ace_0_0.6B_cl/1/26/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21f8fb0ec91ff3cb1156d458eb9363ebe8cf7a737ce8cb7f9d01dd5425c9870
3
+ size 11422929
span_v3/ace_0_0.6B_cl/1/26/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|im_end|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
span_v3/ace_0_0.6B_cl/1/26/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
span_v3/ace_0_0.6B_cl/1/52/README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen3-0.6B
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:Qwen/Qwen3-0.6B
7
+ - lora
8
+ - transformers
9
+ ---
10
+
11
+ # Model Card for Model ID
12
+
13
+ <!-- Provide a quick summary of what the model is/does. -->
14
+
15
+
16
+
17
+ ## Model Details
18
+
19
+ ### Model Description
20
+
21
+ <!-- Provide a longer summary of what this model is. -->
22
+
23
+
24
+
25
+ - **Developed by:** [More Information Needed]
26
+ - **Funded by [optional]:** [More Information Needed]
27
+ - **Shared by [optional]:** [More Information Needed]
28
+ - **Model type:** [More Information Needed]
29
+ - **Language(s) (NLP):** [More Information Needed]
30
+ - **License:** [More Information Needed]
31
+ - **Finetuned from model [optional]:** [More Information Needed]
32
+
33
+ ### Model Sources [optional]
34
+
35
+ <!-- Provide the basic links for the model. -->
36
+
37
+ - **Repository:** [More Information Needed]
38
+ - **Paper [optional]:** [More Information Needed]
39
+ - **Demo [optional]:** [More Information Needed]
40
+
41
+ ## Uses
42
+
43
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
44
+
45
+ ### Direct Use
46
+
47
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
+
49
+ [More Information Needed]
50
+
51
+ ### Downstream Use [optional]
52
+
53
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
54
+
55
+ [More Information Needed]
56
+
57
+ ### Out-of-Scope Use
58
+
59
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
60
+
61
+ [More Information Needed]
62
+
63
+ ## Bias, Risks, and Limitations
64
+
65
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
66
+
67
+ [More Information Needed]
68
+
69
+ ### Recommendations
70
+
71
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
72
+
73
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
74
+
75
+ ## How to Get Started with the Model
76
+
77
+ Use the code below to get started with the model.
78
+
79
+ [More Information Needed]
80
+
81
+ ## Training Details
82
+
83
+ ### Training Data
84
+
85
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
86
+
87
+ [More Information Needed]
88
+
89
+ ### Training Procedure
90
+
91
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
92
+
93
+ #### Preprocessing [optional]
94
+
95
+ [More Information Needed]
96
+
97
+
98
+ #### Training Hyperparameters
99
+
100
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
101
+
102
+ #### Speeds, Sizes, Times [optional]
103
+
104
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
105
+
106
+ [More Information Needed]
107
+
108
+ ## Evaluation
109
+
110
+ <!-- This section describes the evaluation protocols and provides the results. -->
111
+
112
+ ### Testing Data, Factors & Metrics
113
+
114
+ #### Testing Data
115
+
116
+ <!-- This should link to a Dataset Card if possible. -->
117
+
118
+ [More Information Needed]
119
+
120
+ #### Factors
121
+
122
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
123
+
124
+ [More Information Needed]
125
+
126
+ #### Metrics
127
+
128
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
129
+
130
+ [More Information Needed]
131
+
132
+ ### Results
133
+
134
+ [More Information Needed]
135
+
136
+ #### Summary
137
+
138
+
139
+
140
+ ## Model Examination [optional]
141
+
142
+ <!-- Relevant interpretability work for the model goes here -->
143
+
144
+ [More Information Needed]
145
+
146
+ ## Environmental Impact
147
+
148
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
149
+
150
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
151
+
152
+ - **Hardware Type:** [More Information Needed]
153
+ - **Hours used:** [More Information Needed]
154
+ - **Cloud Provider:** [More Information Needed]
155
+ - **Compute Region:** [More Information Needed]
156
+ - **Carbon Emitted:** [More Information Needed]
157
+
158
+ ## Technical Specifications [optional]
159
+
160
+ ### Model Architecture and Objective
161
+
162
+ [More Information Needed]
163
+
164
+ ### Compute Infrastructure
165
+
166
+ [More Information Needed]
167
+
168
+ #### Hardware
169
+
170
+ [More Information Needed]
171
+
172
+ #### Software
173
+
174
+ [More Information Needed]
175
+
176
+ ## Citation [optional]
177
+
178
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
179
+
180
+ **BibTeX:**
181
+
182
+ [More Information Needed]
183
+
184
+ **APA:**
185
+
186
+ [More Information Needed]
187
+
188
+ ## Glossary [optional]
189
+
190
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
191
+
192
+ [More Information Needed]
193
+
194
+ ## More Information [optional]
195
+
196
+ [More Information Needed]
197
+
198
+ ## Model Card Authors [optional]
199
+
200
+ [More Information Needed]
201
+
202
+ ## Model Card Contact
203
+
204
+ [More Information Needed]
205
+ ### Framework versions
206
+
207
+ - PEFT 0.18.1
span_v3/ace_0_0.6B_cl/1/52/adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen3-0.6B",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 128,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.1,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.1",
27
+ "qalora_group_size": 16,
28
+ "r": 64,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "o_proj",
33
+ "up_proj",
34
+ "gate_proj",
35
+ "down_proj",
36
+ "k_proj",
37
+ "q_proj",
38
+ "v_proj"
39
+ ],
40
+ "target_parameters": null,
41
+ "task_type": "CAUSAL_LM",
42
+ "trainable_token_indices": null,
43
+ "use_dora": false,
44
+ "use_qalora": false,
45
+ "use_rslora": false
46
+ }
span_v3/ace_0_0.6B_cl/1/52/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7179320ad97eeb9ea76c04e0e8be6bb93acc1a152b04bf1d5a217a2c70ec5e4
3
+ size 80802963
span_v3/ace_0_0.6B_cl/1/52/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }