saumyamalik commited on
Commit
f0c8dc0
·
1 Parent(s): 33298d1

Add new released models to frozen v1 scores

Browse files
Files changed (1) hide show
  1. leaderboard/final-rbv1-data.csv +11 -0
leaderboard/final-rbv1-data.csv CHANGED
@@ -180,3 +180,14 @@
180
  179,"<a target=""_blank"" href=""https://huggingface.co/stanfordnlp/SteamSHP-flan-t5-large"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">stanfordnlp/SteamSHP-flan-t5-large</a>",Custom Classifier,49.62050475651485,85.75418994413408,33.1140350877193,37.432432432432435,35.62673923719103,62.72974940567991
181
  180,"<a target=""_blank"" href=""https://huggingface.co/allenai/tulu-v2.5-13b-uf-rm"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">allenai/tulu-v2.5-13b-uf-rm</a>",Seq. Classifier,48.05551076423311,39.385474860335194,42.324561403508774,55.54054054054054,47.36897746494243,63.26048833944414
182
  181,"<a target=""_blank"" href=""https://huggingface.co/PKU-Alignment/beaver-7b-v1.0-reward"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">PKU-Alignment/beaver-7b-v1.0-reward</a>",Seq. Classifier,47.26664990676508,81.84357541899442,28.728070175438596,37.567567567567565,34.596155944780925,59.929110947322734
 
 
 
 
 
 
 
 
 
 
 
 
180
  179,"<a target=""_blank"" href=""https://huggingface.co/stanfordnlp/SteamSHP-flan-t5-large"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">stanfordnlp/SteamSHP-flan-t5-large</a>",Custom Classifier,49.62050475651485,85.75418994413408,33.1140350877193,37.432432432432435,35.62673923719103,62.72974940567991
181
  180,"<a target=""_blank"" href=""https://huggingface.co/allenai/tulu-v2.5-13b-uf-rm"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">allenai/tulu-v2.5-13b-uf-rm</a>",Seq. Classifier,48.05551076423311,39.385474860335194,42.324561403508774,55.54054054054054,47.36897746494243,63.26048833944414
182
  181,"<a target=""_blank"" href=""https://huggingface.co/PKU-Alignment/beaver-7b-v1.0-reward"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">PKU-Alignment/beaver-7b-v1.0-reward</a>",Seq. Classifier,47.26664990676508,81.84357541899442,28.728070175438596,37.567567567567565,34.596155944780925,59.929110947322734
183
+ 182,"<a target=""_blank"" href=""https://huggingface.co/allenai/Llama-3.1-70B-Instruct-RM-RB2"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">allenai/Llama-3.1-70B-Instruct-RM-RB2</a>",Seq. Classifier,90.20891847250666,96.64804469273743,83.55263157894737,90.94594594594595,89.68905167239592,0.0
184
+ 183,"<a target=""_blank"" href=""https://huggingface.co/allenai/Llama-3.1-8B-Instruct-RM-RB2"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">allenai/Llama-3.1-8B-Instruct-RM-RB2</a>",Seq. Classifier,88.85411761564486,95.81005586592178,81.57894736842105,89.32432432432432,88.70314290391227,0.0
185
+ 184,"<a target=""_blank"" href=""https://huggingface.co/allenai/Llama-3.1-8B-Base-RM-RB2"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">allenai/Llama-3.1-8B-Base-RM-RB2</a>",Seq. Classifier,84.63022615056406,93.29608938547486,77.85087719298247,88.51351351351352,78.86042451028537,0.0
186
+ 185,"<a target=""_blank"" href=""https://huggingface.co/allenai/Llama-3.1-Tulu-3-8B-SFT-RM-RB2"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">allenai/Llama-3.1-Tulu-3-8B-SFT-RM-RB2</a>",Seq. Classifier,85.5067097271751,94.97206703910615,79.16666666666666,87.83783783783784,80.05026736508975,0.0
187
+ 186,"<a target=""_blank"" href=""https://huggingface.co/allenai/Llama-3.1-Tulu-3-8B-DPO-RM-RB2"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">allenai/Llama-3.1-Tulu-3-8B-DPO-RM-RB2</a>",Seq. Classifier,84.30783781180817,95.53072625698324,76.09649122807018,86.62162162162163,78.98251214055765,0.0
188
+ 187,"<a target=""_blank"" href=""https://huggingface.co/allenai/Llama-3.1-Tulu-3-8B-RL-RM-RB2"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">allenai/Llama-3.1-Tulu-3-8B-RL-RM-RB2</a>",Seq. Classifier,83.68729455170623,94.6927374301676,75.87719298245614,87.02702702702703,77.15222076717411,0.0
189
+ 188,"<a target=""_blank"" href=""https://huggingface.co/allenai/Llama-3.1-Tulu-3-70B-SFT-RM-RB2"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">allenai/Llama-3.1-Tulu-3-70B-SFT-RM-RB2</a>",Seq. Classifier,88.9245750153865,96.92737430167597,82.67543859649122,90.27027027027027,85.82521689310852,0.0
190
+
191
+
192
+
193
+