nsthorat-lilac commited on
Commit
02f502d
1 Parent(s): 494bc5a

Push to HF space

Browse files
Files changed (1) hide show
  1. data/lilac.yml +435 -0
data/lilac.yml CHANGED
@@ -228,6 +228,12 @@ datasets:
228
  version: null
229
  draft: main
230
  signal_name: concept_score
 
 
 
 
 
 
231
  settings:
232
  ui:
233
  media_paths:
@@ -399,6 +405,12 @@ datasets:
399
  version: null
400
  draft: main
401
  signal_name: concept_score
 
 
 
 
 
 
402
  settings:
403
  ui:
404
  media_paths:
@@ -562,6 +574,12 @@ datasets:
562
  version: null
563
  draft: main
564
  signal_name: concept_score
 
 
 
 
 
 
565
  settings:
566
  ui:
567
  media_paths:
@@ -2836,6 +2854,355 @@ datasets:
2836
  version: null
2837
  draft: main
2838
  signal_name: concept_score
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2839
  settings:
2840
  ui:
2841
  media_paths:
@@ -3415,6 +3782,18 @@ datasets:
3415
  version: null
3416
  draft: main
3417
  signal_name: concept_score
 
 
 
 
 
 
 
 
 
 
 
 
3418
  settings:
3419
  ui:
3420
  media_paths:
@@ -3807,6 +4186,22 @@ datasets:
3807
  version: null
3808
  draft: main
3809
  signal_name: concept_score
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3810
  settings:
3811
  ui:
3812
  media_paths:
@@ -3973,6 +4368,12 @@ datasets:
3973
  version: null
3974
  draft: main
3975
  signal_name: concept_score
 
 
 
 
 
 
3976
  settings:
3977
  ui:
3978
  media_paths:
@@ -4136,6 +4537,12 @@ datasets:
4136
  version: null
4137
  draft: main
4138
  signal_name: concept_score
 
 
 
 
 
 
4139
  settings:
4140
  ui:
4141
  media_paths:
@@ -4298,6 +4705,12 @@ datasets:
4298
  version: null
4299
  draft: main
4300
  signal_name: concept_score
 
 
 
 
 
 
4301
  settings:
4302
  ui:
4303
  media_paths:
@@ -4609,6 +5022,28 @@ datasets:
4609
  version: null
4610
  draft: main
4611
  signal_name: concept_score
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4612
  settings:
4613
  ui:
4614
  media_paths:
 
228
  version: null
229
  draft: main
230
  signal_name: concept_score
231
+ - path: text
232
+ signal:
233
+ embedding: gte-small
234
+ eps: 0.05
235
+ min_samples: 5
236
+ signal_name: cluster_dbscan
237
  settings:
238
  ui:
239
  media_paths:
 
405
  version: null
406
  draft: main
407
  signal_name: concept_score
408
+ - path: text
409
+ signal:
410
+ embedding: gte-small
411
+ eps: 0.05
412
+ min_samples: 5
413
+ signal_name: cluster_dbscan
414
  settings:
415
  ui:
416
  media_paths:
 
574
  version: null
575
  draft: main
576
  signal_name: concept_score
577
+ - path: text
578
+ signal:
579
+ embedding: gte-small
580
+ eps: 0.05
581
+ min_samples: 5
582
+ signal_name: cluster_dbscan
583
  settings:
584
  ui:
585
  media_paths:
 
2854
  version: null
2855
  draft: main
2856
  signal_name: concept_score
2857
+ - path: original-instruction
2858
+ signal:
2859
+ embedding: gte-small
2860
+ eps: 0.05
2861
+ min_samples: 5
2862
+ signal_name: cluster_dbscan
2863
+ - path: original-instruction
2864
+ signal:
2865
+ embedding: gte-small
2866
+ namespace: lilac
2867
+ concept_name: legal-termination
2868
+ version: null
2869
+ draft: main
2870
+ signal_name: concept_score
2871
+ - path: original-instruction
2872
+ signal:
2873
+ embedding: gte-small
2874
+ namespace: lilac
2875
+ concept_name: negative-sentiment
2876
+ version: null
2877
+ draft: main
2878
+ signal_name: concept_score
2879
+ - path: original-instruction
2880
+ signal:
2881
+ embedding: gte-small
2882
+ namespace: lilac
2883
+ concept_name: non-english
2884
+ version: null
2885
+ draft: main
2886
+ signal_name: concept_score
2887
+ - path: original-instruction
2888
+ signal:
2889
+ embedding: gte-small
2890
+ namespace: lilac
2891
+ concept_name: positive-sentiment
2892
+ version: null
2893
+ draft: main
2894
+ signal_name: concept_score
2895
+ - path: original-instruction
2896
+ signal:
2897
+ embedding: gte-small
2898
+ namespace: lilac
2899
+ concept_name: profanity
2900
+ version: null
2901
+ draft: main
2902
+ signal_name: concept_score
2903
+ - path: original-instruction
2904
+ signal:
2905
+ embedding: gte-small
2906
+ namespace: lilac
2907
+ concept_name: question
2908
+ version: null
2909
+ draft: main
2910
+ signal_name: concept_score
2911
+ - path: original-instruction
2912
+ signal:
2913
+ embedding: gte-small
2914
+ namespace: lilac
2915
+ concept_name: source-code
2916
+ version: null
2917
+ draft: main
2918
+ signal_name: concept_score
2919
+ - path: original-instruction
2920
+ signal:
2921
+ embedding: gte-small
2922
+ namespace: lilac
2923
+ concept_name: toxicity
2924
+ version: null
2925
+ draft: main
2926
+ signal_name: concept_score
2927
+ - path: original-context
2928
+ signal:
2929
+ embedding: gte-small
2930
+ eps: 0.05
2931
+ min_samples: 5
2932
+ signal_name: cluster_dbscan
2933
+ - path: original-response
2934
+ signal:
2935
+ embedding: gte-small
2936
+ eps: 0.05
2937
+ min_samples: 5
2938
+ signal_name: cluster_dbscan
2939
+ - path: original-response
2940
+ signal:
2941
+ embedding: gte-small
2942
+ namespace: lilac
2943
+ concept_name: legal-termination
2944
+ version: null
2945
+ draft: main
2946
+ signal_name: concept_score
2947
+ - path: original-response
2948
+ signal:
2949
+ embedding: gte-small
2950
+ namespace: lilac
2951
+ concept_name: negative-sentiment
2952
+ version: null
2953
+ draft: main
2954
+ signal_name: concept_score
2955
+ - path: original-response
2956
+ signal:
2957
+ embedding: gte-small
2958
+ namespace: lilac
2959
+ concept_name: non-english
2960
+ version: null
2961
+ draft: main
2962
+ signal_name: concept_score
2963
+ - path: original-response
2964
+ signal:
2965
+ embedding: gte-small
2966
+ namespace: lilac
2967
+ concept_name: positive-sentiment
2968
+ version: null
2969
+ draft: main
2970
+ signal_name: concept_score
2971
+ - path: original-response
2972
+ signal:
2973
+ embedding: gte-small
2974
+ namespace: lilac
2975
+ concept_name: profanity
2976
+ version: null
2977
+ draft: main
2978
+ signal_name: concept_score
2979
+ - path: original-response
2980
+ signal:
2981
+ embedding: gte-small
2982
+ namespace: lilac
2983
+ concept_name: question
2984
+ version: null
2985
+ draft: main
2986
+ signal_name: concept_score
2987
+ - path: original-response
2988
+ signal:
2989
+ embedding: gte-small
2990
+ namespace: lilac
2991
+ concept_name: source-code
2992
+ version: null
2993
+ draft: main
2994
+ signal_name: concept_score
2995
+ - path: original-response
2996
+ signal:
2997
+ embedding: gte-small
2998
+ namespace: lilac
2999
+ concept_name: toxicity
3000
+ version: null
3001
+ draft: main
3002
+ signal_name: concept_score
3003
+ - path:
3004
+ - new-instruction
3005
+ - value
3006
+ - '*'
3007
+ signal:
3008
+ embedding: gte-small
3009
+ eps: 0.05
3010
+ min_samples: 5
3011
+ signal_name: cluster_dbscan
3012
+ - path:
3013
+ - new-instruction
3014
+ - value
3015
+ - '*'
3016
+ signal:
3017
+ embedding: gte-small
3018
+ namespace: lilac
3019
+ concept_name: legal-termination
3020
+ version: null
3021
+ draft: main
3022
+ signal_name: concept_score
3023
+ - path:
3024
+ - new-instruction
3025
+ - value
3026
+ - '*'
3027
+ signal:
3028
+ embedding: gte-small
3029
+ namespace: lilac
3030
+ concept_name: negative-sentiment
3031
+ version: null
3032
+ draft: main
3033
+ signal_name: concept_score
3034
+ - path:
3035
+ - new-instruction
3036
+ - value
3037
+ - '*'
3038
+ signal:
3039
+ embedding: gte-small
3040
+ namespace: lilac
3041
+ concept_name: non-english
3042
+ version: null
3043
+ draft: main
3044
+ signal_name: concept_score
3045
+ - path:
3046
+ - new-instruction
3047
+ - value
3048
+ - '*'
3049
+ signal:
3050
+ embedding: gte-small
3051
+ namespace: lilac
3052
+ concept_name: positive-sentiment
3053
+ version: null
3054
+ draft: main
3055
+ signal_name: concept_score
3056
+ - path:
3057
+ - new-instruction
3058
+ - value
3059
+ - '*'
3060
+ signal:
3061
+ embedding: gte-small
3062
+ namespace: lilac
3063
+ concept_name: profanity
3064
+ version: null
3065
+ draft: main
3066
+ signal_name: concept_score
3067
+ - path:
3068
+ - new-instruction
3069
+ - value
3070
+ - '*'
3071
+ signal:
3072
+ embedding: gte-small
3073
+ namespace: lilac
3074
+ concept_name: question
3075
+ version: null
3076
+ draft: main
3077
+ signal_name: concept_score
3078
+ - path:
3079
+ - new-instruction
3080
+ - value
3081
+ - '*'
3082
+ signal:
3083
+ embedding: gte-small
3084
+ namespace: lilac
3085
+ concept_name: source-code
3086
+ version: null
3087
+ draft: main
3088
+ signal_name: concept_score
3089
+ - path:
3090
+ - new-instruction
3091
+ - value
3092
+ - '*'
3093
+ signal:
3094
+ embedding: gte-small
3095
+ namespace: lilac
3096
+ concept_name: toxicity
3097
+ version: null
3098
+ draft: main
3099
+ signal_name: concept_score
3100
+ - path:
3101
+ - new-context
3102
+ - value
3103
+ - '*'
3104
+ signal:
3105
+ embedding: gte-small
3106
+ eps: 0.05
3107
+ min_samples: 5
3108
+ signal_name: cluster_dbscan
3109
+ - path:
3110
+ - new-response
3111
+ - value
3112
+ - '*'
3113
+ signal:
3114
+ embedding: gte-small
3115
+ eps: 0.05
3116
+ min_samples: 5
3117
+ signal_name: cluster_dbscan
3118
+ - path:
3119
+ - new-response
3120
+ - value
3121
+ - '*'
3122
+ signal:
3123
+ embedding: gte-small
3124
+ namespace: lilac
3125
+ concept_name: legal-termination
3126
+ version: null
3127
+ draft: main
3128
+ signal_name: concept_score
3129
+ - path:
3130
+ - new-response
3131
+ - value
3132
+ - '*'
3133
+ signal:
3134
+ embedding: gte-small
3135
+ namespace: lilac
3136
+ concept_name: negative-sentiment
3137
+ version: null
3138
+ draft: main
3139
+ signal_name: concept_score
3140
+ - path:
3141
+ - new-response
3142
+ - value
3143
+ - '*'
3144
+ signal:
3145
+ embedding: gte-small
3146
+ namespace: lilac
3147
+ concept_name: non-english
3148
+ version: null
3149
+ draft: main
3150
+ signal_name: concept_score
3151
+ - path:
3152
+ - new-response
3153
+ - value
3154
+ - '*'
3155
+ signal:
3156
+ embedding: gte-small
3157
+ namespace: lilac
3158
+ concept_name: positive-sentiment
3159
+ version: null
3160
+ draft: main
3161
+ signal_name: concept_score
3162
+ - path:
3163
+ - new-response
3164
+ - value
3165
+ - '*'
3166
+ signal:
3167
+ embedding: gte-small
3168
+ namespace: lilac
3169
+ concept_name: profanity
3170
+ version: null
3171
+ draft: main
3172
+ signal_name: concept_score
3173
+ - path:
3174
+ - new-response
3175
+ - value
3176
+ - '*'
3177
+ signal:
3178
+ embedding: gte-small
3179
+ namespace: lilac
3180
+ concept_name: question
3181
+ version: null
3182
+ draft: main
3183
+ signal_name: concept_score
3184
+ - path:
3185
+ - new-response
3186
+ - value
3187
+ - '*'
3188
+ signal:
3189
+ embedding: gte-small
3190
+ namespace: lilac
3191
+ concept_name: source-code
3192
+ version: null
3193
+ draft: main
3194
+ signal_name: concept_score
3195
+ - path:
3196
+ - new-response
3197
+ - value
3198
+ - '*'
3199
+ signal:
3200
+ embedding: gte-small
3201
+ namespace: lilac
3202
+ concept_name: toxicity
3203
+ version: null
3204
+ draft: main
3205
+ signal_name: concept_score
3206
  settings:
3207
  ui:
3208
  media_paths:
 
3782
  version: null
3783
  draft: main
3784
  signal_name: concept_score
3785
+ - path: question
3786
+ signal:
3787
+ embedding: gte-small
3788
+ eps: 0.05
3789
+ min_samples: 5
3790
+ signal_name: cluster_dbscan
3791
+ - path: response
3792
+ signal:
3793
+ embedding: gte-small
3794
+ eps: 0.05
3795
+ min_samples: 5
3796
+ signal_name: cluster_dbscan
3797
  settings:
3798
  ui:
3799
  media_paths:
 
4186
  version: null
4187
  draft: main
4188
  signal_name: concept_score
4189
+ - path:
4190
+ - translation
4191
+ - es
4192
+ signal:
4193
+ embedding: gte-small
4194
+ eps: 0.05
4195
+ min_samples: 5
4196
+ signal_name: cluster_dbscan
4197
+ - path:
4198
+ - translation
4199
+ - en
4200
+ signal:
4201
+ embedding: gte-small
4202
+ eps: 0.05
4203
+ min_samples: 5
4204
+ signal_name: cluster_dbscan
4205
  settings:
4206
  ui:
4207
  media_paths:
 
4368
  version: null
4369
  draft: main
4370
  signal_name: concept_score
4371
+ - path: lecture
4372
+ signal:
4373
+ embedding: gte-small
4374
+ eps: 0.05
4375
+ min_samples: 5
4376
+ signal_name: cluster_dbscan
4377
  settings:
4378
  ui:
4379
  media_paths:
 
4537
  version: null
4538
  draft: main
4539
  signal_name: concept_score
4540
+ - path: text
4541
+ signal:
4542
+ embedding: gte-small
4543
+ eps: 0.05
4544
+ min_samples: 5
4545
+ signal_name: cluster_dbscan
4546
  settings:
4547
  ui:
4548
  media_paths:
 
4705
  version: null
4706
  draft: main
4707
  signal_name: concept_score
4708
+ - path: overview
4709
+ signal:
4710
+ embedding: gte-small
4711
+ eps: 0.05
4712
+ min_samples: 5
4713
+ signal_name: cluster_dbscan
4714
  settings:
4715
  ui:
4716
  media_paths:
 
5022
  version: null
5023
  draft: main
5024
  signal_name: concept_score
5025
+ - path:
5026
+ - outline
5027
+ - '*'
5028
+ signal:
5029
+ embedding: gte-small
5030
+ eps: 0.05
5031
+ min_samples: 5
5032
+ signal_name: cluster_dbscan
5033
+ - path:
5034
+ - concepts
5035
+ - '*'
5036
+ signal:
5037
+ embedding: gte-small
5038
+ eps: 0.05
5039
+ min_samples: 5
5040
+ signal_name: cluster_dbscan
5041
+ - path: markdown
5042
+ signal:
5043
+ embedding: gte-small
5044
+ eps: 0.05
5045
+ min_samples: 5
5046
+ signal_name: cluster_dbscan
5047
  settings:
5048
  ui:
5049
  media_paths: