Update README.md

README.md

@@ -88,7 +88,7 @@ model-index:
       type: Coreference resolution
     dataset:
       type: winogrande
-      name: Winogrande XL
+      name: Winogrande XL (xl)
       config: xl
       split: validation
       revision: a80f460359d1e9a67c006011c94de42a8759430c
@@ -99,7 +99,7 @@ model-index:
       type: Coreference resolution
     dataset:
       type: Muennighoff/xwinograd
-      name: XWinograd
+      name: XWinograd (en)
       config: en
       split: test
       revision: 9dd5ea5505fad86b7bedad667955577815300cee
@@ -110,7 +110,7 @@ model-index:
       type: Coreference resolution
     dataset:
       type: Muennighoff/xwinograd
-      name: XWinograd
+      name: XWinograd (fr)
       config: fr
       split: test
       revision: 9dd5ea5505fad86b7bedad667955577815300cee
@@ -121,7 +121,7 @@ model-index:
       type: Coreference resolution
     dataset:
       type: Muennighoff/xwinograd
-      name: XWinograd
+      name: XWinograd (jp)
       config: jp
       split: test
       revision: 9dd5ea5505fad86b7bedad667955577815300cee
@@ -132,7 +132,7 @@ model-index:
       type: Coreference resolution
     dataset:
       type: Muennighoff/xwinograd
-      name: XWinograd
+      name: XWinograd (pt)
       config: pt
       split: test
       revision: 9dd5ea5505fad86b7bedad667955577815300cee
@@ -143,7 +143,7 @@ model-index:
       type: Coreference resolution
     dataset:
       type: Muennighoff/xwinograd
-      name: XWinograd
+      name: XWinograd (ru)
       config: ru
       split: test
       revision: 9dd5ea5505fad86b7bedad667955577815300cee
@@ -154,7 +154,7 @@ model-index:
       type: Coreference resolution
     dataset:
       type: Muennighoff/xwinograd
-      name: XWinograd
+      name: XWinograd (zh)
       config: zh
       split: test
       revision: 9dd5ea5505fad86b7bedad667955577815300cee
@@ -165,7 +165,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: anli
-      name: ANLI
+      name: ANLI (r1)
       config: r1
       split: validation
       revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
@@ -176,7 +176,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: anli
-      name: ANLI
+      name: ANLI (r2)
       config: r2
       split: validation
       revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
@@ -187,7 +187,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: anli
-      name: ANLI
+      name: ANLI (r3)
       config: r3
       split: validation
       revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
@@ -198,7 +198,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: super_glue
-      name: SuperGLUE
+      name: SuperGLUE (cb)
       config: cb
       split: validation
       revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
@@ -209,7 +209,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: super_glue
-      name: SuperGLUE
+      name: SuperGLUE (rte)
       config: rte
       split: validation
       revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
@@ -220,7 +220,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: xnli
-      name: XNLI
+      name: XNLI (ar)
       config: ar
       split: validation
       revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
@@ -231,7 +231,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: xnli
-      name: XNLI
+      name: XNLI (bg)
       config: bg
       split: validation
       revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
@@ -242,7 +242,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: xnli
-      name: XNLI
+      name: XNLI (de)
       config: de
       split: validation
       revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
@@ -253,7 +253,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: xnli
-      name: XNLI
+      name: XNLI (el)
       config: el
       split: validation
       revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
@@ -264,7 +264,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: xnli
-      name: XNLI
+      name: XNLI (en)
       config: en
       split: validation
       revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
@@ -275,7 +275,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: xnli
-      name: XNLI
+      name: XNLI (es)
       config: es
       split: validation
       revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
@@ -286,7 +286,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: xnli
-      name: XNLI
+      name: XNLI (fr)
       config: fr
       split: validation
       revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
@@ -297,7 +297,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: xnli
-      name: XNLI
+      name: XNLI (hi)
       config: hi
       split: validation
       revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
@@ -308,7 +308,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: xnli
-      name: XNLI
+      name: XNLI (ru)
       config: ru
       split: validation
       revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
@@ -319,7 +319,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: xnli
-      name: XNLI
+      name: XNLI (sw)
       config: sw
       split: validation
       revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
@@ -330,7 +330,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: xnli
-      name: XNLI
+      name: XNLI (th)
       config: th
       split: validation
       revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
@@ -341,7 +341,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: xnli
-      name: XNLI
+      name: XNLI (tr)
       config: tr
       split: validation
       revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
@@ -352,7 +352,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: xnli
-      name: XNLI
+      name: XNLI (ur)
       config: ur
       split: validation
       revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
@@ -363,7 +363,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: xnli
-      name: XNLI
+      name: XNLI (vi)
       config: vi
       split: validation
       revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
@@ -374,7 +374,7 @@ model-index:
       type: Natural language inference
     dataset:
       type: xnli
-      name: XNLI
+      name: XNLI (zh)
       config: zh
       split: validation
       revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
@@ -385,7 +385,8 @@ model-index:
       type: Program synthesis
     dataset:
       type: openai_humaneval
-      name: HumanEval
+      name: HumanEval (None)
+      config: None
       split: test
       revision: e8dc562f5de170c54b5481011dd9f4fa04845771
     metrics:
@@ -399,7 +400,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: story_cloze
-      name: StoryCloze
+      name: StoryCloze (2016)
       config: "2016"
       split: validation
       revision: e724c6f8cdf7c7a2fb229d862226e15b023ee4db
@@ -410,7 +411,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: super_glue
-      name: SuperGLUE
+      name: SuperGLUE (copa)
       config: copa
       split: validation
       revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
@@ -421,7 +422,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: xcopa
-      name: XCOPA
+      name: XCOPA (et)
       config: et
       split: validation
       revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
@@ -432,7 +433,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: xcopa
-      name: XCOPA
+      name: XCOPA (ht)
       config: ht
       split: validation
       revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
@@ -443,7 +444,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: xcopa
-      name: XCOPA
+      name: XCOPA (id)
       config: id
       split: validation
       revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
@@ -454,7 +455,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: xcopa
-      name: XCOPA
+      name: XCOPA (it)
       config: it
       split: validation
       revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
@@ -465,7 +466,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: xcopa
-      name: XCOPA
+      name: XCOPA (qu)
       config: qu
       split: validation
       revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
@@ -476,7 +477,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: xcopa
-      name: XCOPA
+      name: XCOPA (sw)
       config: sw
       split: validation
       revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
@@ -487,7 +488,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: xcopa
-      name: XCOPA
+      name: XCOPA (ta)
       config: ta
       split: validation
       revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
@@ -498,7 +499,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: xcopa
-      name: XCOPA
+      name: XCOPA (th)
       config: th
       split: validation
       revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
@@ -509,7 +510,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: xcopa
-      name: XCOPA
+      name: XCOPA (tr)
       config: tr
       split: validation
       revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
@@ -520,7 +521,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: xcopa
-      name: XCOPA
+      name: XCOPA (vi)
       config: vi
       split: validation
       revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
@@ -531,7 +532,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: xcopa
-      name: XCOPA
+      name: XCOPA (zh)
       config: zh
       split: validation
       revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
@@ -542,7 +543,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: Muennighoff/xstory_cloze
-      name: XStoryCloze
+      name: XStoryCloze (ar)
       config: ar
       split: validation
       revision: 8bb76e594b68147f1a430e86829d07189622b90d
@@ -553,7 +554,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: Muennighoff/xstory_cloze
-      name: XStoryCloze
+      name: XStoryCloze (es)
       config: es
       split: validation
       revision: 8bb76e594b68147f1a430e86829d07189622b90d
@@ -564,7 +565,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: Muennighoff/xstory_cloze
-      name: XStoryCloze
+      name: XStoryCloze (eu)
       config: eu
       split: validation
       revision: 8bb76e594b68147f1a430e86829d07189622b90d
@@ -575,7 +576,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: Muennighoff/xstory_cloze
-      name: XStoryCloze
+      name: XStoryCloze (hi)
       config: hi
       split: validation
       revision: 8bb76e594b68147f1a430e86829d07189622b90d
@@ -586,7 +587,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: Muennighoff/xstory_cloze
-      name: XStoryCloze
+      name: XStoryCloze (id)
       config: id
       split: validation
       revision: 8bb76e594b68147f1a430e86829d07189622b90d
@@ -597,7 +598,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: Muennighoff/xstory_cloze
-      name: XStoryCloze
+      name: XStoryCloze (my)
       config: my
       split: validation
       revision: 8bb76e594b68147f1a430e86829d07189622b90d
@@ -608,7 +609,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: Muennighoff/xstory_cloze
-      name: XStoryCloze
+      name: XStoryCloze (ru)
       config: ru
       split: validation
       revision: 8bb76e594b68147f1a430e86829d07189622b90d
@@ -619,7 +620,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: Muennighoff/xstory_cloze
-      name: XStoryCloze
+      name: XStoryCloze (sw)
       config: sw
       split: validation
       revision: 8bb76e594b68147f1a430e86829d07189622b90d
@@ -630,7 +631,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: Muennighoff/xstory_cloze
-      name: XStoryCloze
+      name: XStoryCloze (te)
       config: te
       split: validation
       revision: 8bb76e594b68147f1a430e86829d07189622b90d
@@ -641,7 +642,7 @@ model-index:
       type: Sentence completion
     dataset:
       type: Muennighoff/xstory_cloze
-      name: XStoryCloze
+      name: XStoryCloze (zh)
       config: zh
       split: validation
       revision: 8bb76e594b68147f1a430e86829d07189622b90d