Spaces:
Runtime error
Runtime error
Current evals
Browse files- data/code_eval_board.csv +4 -5
data/code_eval_board.csv
CHANGED
|
@@ -5,6 +5,7 @@ T,Models,ARC,HellaSwag,MMLU,TruthfulQA,Winogrande,GSM8K,Reference Model
|
|
| 5 |
π’,mistralai/Mistral-7B-v0.1,0.54,0.51,0.46,0.75,0,0.91,huggyllama/llama-7b
|
| 6 |
πΆ,rishiraj/meow,0.11,0.49,0.28,0.36,0.02,0.95,huggyllama/llama-7b
|
| 7 |
πΆ,Q-bert/MetaMath-Cybertron-Starling,0.52,0.64,0.51,0.75,0.01,0.99,huggyllama/llama-7b
|
|
|
|
| 8 |
πΆ,AIDC-ai-business/Marcoroni-7B-v3,0.1,0.14,0.2,0.41,0.0,0.95,mistralai/Mistral-7B-v0.1
|
| 9 |
πΆ,amazon/MistralLite,0.09,0.14,0.2,0.43,0.0,0.73,mistralai/Mistral-7B-v0.1
|
| 10 |
πΆ,openchat/openchat_3.5,0.13,0.13,0.23,0.45,0.0,0.97,mistralai/Mistral-7B-v0.1
|
|
@@ -13,6 +14,7 @@ T,Models,ARC,HellaSwag,MMLU,TruthfulQA,Winogrande,GSM8K,Reference Model
|
|
| 13 |
πΆ,microsoft/Orca-2-7b,0.88,0.8,0.77,0.91,0.0,1.0,mistralai/Mistral-7B-v0.1
|
| 14 |
πΆ,WizardLM/WizardMath-7B-V1.1,0.1,0.11,0.21,0.4,0.0,0.99,mistralai/Mistral-7B-v0.1
|
| 15 |
πΆ,01-ai/Yi-6B-200K,0.19,0.3,0.3,0.6,0.0,0.93,mistralai/Mistral-7B-v0.1
|
|
|
|
| 16 |
πΆ,mistralai/Mistral-7B-Instruct-v0.2,0.06,0.21,0.17,0.48,0.0,0.95,mistralai/Mistral-7B-v0.1
|
| 17 |
πΆ,Yhyu13/LMCocktail-10.7B-v1,0.1,0.44,0.23,0.51,0.0,0.97,mistralai/Mistral-7B-v0.1
|
| 18 |
πΆ,ehartford/dolphin-2.1-mistral-7b,0.08,0.1,0.2,0.4,0.0,0.92,mistralai/Mistral-7B-v0.1
|
|
@@ -32,14 +34,11 @@ T,Models,ARC,HellaSwag,MMLU,TruthfulQA,Winogrande,GSM8K,Reference Model
|
|
| 32 |
π’,huggyllama/llama-7b,0.11,0.17,0.22,0.46,0.0,0.79,mistralai/Mistral-7B-v0.1
|
| 33 |
π’,tiiuae/falcon-7b-instruct,0.06,0.16,0.19,0.56,0.0,0.98,mistralai/Mistral-7B-v0.1
|
| 34 |
πΆ,NousResearch/Nous-Hermes-llama-2-7b,0.09,0.18,0.26,0.5,0.0,0.96,mistralai/Mistral-7B-v0.1
|
| 35 |
-
πΆ,openaccess-ai-collective/DPOpenHermes-7B-v2,0.08,0.11,0.22,0.41,0.0,0.96,mistralai/Mistral-7B-v0.1
|
| 36 |
-
π’,01-ai/Yi-6B,0.28,0.32,0.3,0.62,0.02,0.94,mistralai/Mistral-7B-v0.1
|
| 37 |
πΆ,Intel/neural-chat-7b-v3-1,0.1,0.15,0.18,0.49,0.0,0.81,mistralai/Mistral-7B-v0.1
|
| 38 |
πΆ,fblgit/juanako-7b-UNA,0.09,0.15,0.18,0.46,0.0,0.81,mistralai/Mistral-7B-v0.1
|
| 39 |
πΆ,Intel/neural-chat-7b-v3-2,0.12,0.14,0.2,0.5,0.0,0.93,mistralai/Mistral-7B-v0.1
|
| 40 |
πΆ,fblgit/una-cybertron-7b-v2-bf16,0.1,0.12,0.21,0.46,0.0,0.92,mistralai/Mistral-7B-v0.1
|
| 41 |
-
πΆ,Intel/neural-chat-7b-v3-3,0.06,0.15,0.18,0.47,0.0,0.98,mistralai/Mistral-7B-v0.1
|
| 42 |
πΆ,fblgit/una-cybertron-7b-v3-OMA,0.04,0.16,0.17,0.36,0.0,0.94,mistralai/Mistral-7B-v0.1
|
| 43 |
-
πΆ,fblgit/una-xaberius-34b-v1beta,0.37,0.54,0.33,0.61,0.04,0.96,huggyllama/llama-7b
|
| 44 |
-
πΆ,upstage/SOLAR-10.7B-Instruct-v1.0,0.11,0.49,0.28,0.36,0.01,0.96,huggyllama/llama-7b
|
| 45 |
πΆ,VAGOsolutions/SauerkrautLM-SOLAR-Instruct,0.12,0.54,0.32,0.34,0.01,0.96,huggyllama/llama-7b
|
|
|
|
|
|
|
|
|
| 5 |
π’,mistralai/Mistral-7B-v0.1,0.54,0.51,0.46,0.75,0,0.91,huggyllama/llama-7b
|
| 6 |
πΆ,rishiraj/meow,0.11,0.49,0.28,0.36,0.02,0.95,huggyllama/llama-7b
|
| 7 |
πΆ,Q-bert/MetaMath-Cybertron-Starling,0.52,0.64,0.51,0.75,0.01,0.99,huggyllama/llama-7b
|
| 8 |
+
πΆ,upstage/SOLAR-10.7B-Instruct-v1.0,0.11,0.49,0.28,0.36,0.01,0.96,huggyllama/llama-7b
|
| 9 |
πΆ,AIDC-ai-business/Marcoroni-7B-v3,0.1,0.14,0.2,0.41,0.0,0.95,mistralai/Mistral-7B-v0.1
|
| 10 |
πΆ,amazon/MistralLite,0.09,0.14,0.2,0.43,0.0,0.73,mistralai/Mistral-7B-v0.1
|
| 11 |
πΆ,openchat/openchat_3.5,0.13,0.13,0.23,0.45,0.0,0.97,mistralai/Mistral-7B-v0.1
|
|
|
|
| 14 |
πΆ,microsoft/Orca-2-7b,0.88,0.8,0.77,0.91,0.0,1.0,mistralai/Mistral-7B-v0.1
|
| 15 |
πΆ,WizardLM/WizardMath-7B-V1.1,0.1,0.11,0.21,0.4,0.0,0.99,mistralai/Mistral-7B-v0.1
|
| 16 |
πΆ,01-ai/Yi-6B-200K,0.19,0.3,0.3,0.6,0.0,0.93,mistralai/Mistral-7B-v0.1
|
| 17 |
+
πΆ,Intel/neural-chat-7b-v3-3,0.06,0.15,0.18,0.47,0.0,0.98,mistralai/Mistral-7B-v0.1
|
| 18 |
πΆ,mistralai/Mistral-7B-Instruct-v0.2,0.06,0.21,0.17,0.48,0.0,0.95,mistralai/Mistral-7B-v0.1
|
| 19 |
πΆ,Yhyu13/LMCocktail-10.7B-v1,0.1,0.44,0.23,0.51,0.0,0.97,mistralai/Mistral-7B-v0.1
|
| 20 |
πΆ,ehartford/dolphin-2.1-mistral-7b,0.08,0.1,0.2,0.4,0.0,0.92,mistralai/Mistral-7B-v0.1
|
|
|
|
| 34 |
π’,huggyllama/llama-7b,0.11,0.17,0.22,0.46,0.0,0.79,mistralai/Mistral-7B-v0.1
|
| 35 |
π’,tiiuae/falcon-7b-instruct,0.06,0.16,0.19,0.56,0.0,0.98,mistralai/Mistral-7B-v0.1
|
| 36 |
πΆ,NousResearch/Nous-Hermes-llama-2-7b,0.09,0.18,0.26,0.5,0.0,0.96,mistralai/Mistral-7B-v0.1
|
|
|
|
|
|
|
| 37 |
πΆ,Intel/neural-chat-7b-v3-1,0.1,0.15,0.18,0.49,0.0,0.81,mistralai/Mistral-7B-v0.1
|
| 38 |
πΆ,fblgit/juanako-7b-UNA,0.09,0.15,0.18,0.46,0.0,0.81,mistralai/Mistral-7B-v0.1
|
| 39 |
πΆ,Intel/neural-chat-7b-v3-2,0.12,0.14,0.2,0.5,0.0,0.93,mistralai/Mistral-7B-v0.1
|
| 40 |
πΆ,fblgit/una-cybertron-7b-v2-bf16,0.1,0.12,0.21,0.46,0.0,0.92,mistralai/Mistral-7B-v0.1
|
|
|
|
| 41 |
πΆ,fblgit/una-cybertron-7b-v3-OMA,0.04,0.16,0.17,0.36,0.0,0.94,mistralai/Mistral-7B-v0.1
|
|
|
|
|
|
|
| 42 |
πΆ,VAGOsolutions/SauerkrautLM-SOLAR-Instruct,0.12,0.54,0.32,0.34,0.01,0.96,huggyllama/llama-7b
|
| 43 |
+
πΆ,openaccess-ai-collective/DPOpenHermes-7B-v2,0.08,0.11,0.22,0.41,0.0,0.96,mistralai/Mistral-7B-v0.1
|
| 44 |
+
π’,01-ai/Yi-6B,0.28,0.32,0.3,0.62,0.02,0.94,mistralai/Mistral-7B-v0.1
|