current evals

data/code_eval_board.csv

@@ -18,4 +18,6 @@ T,Models,ARC,HellaSwag,MMLU,TruthfulQA,Winogrande,GSM8K,Reference Model
 🔶,mistralai/Mistral-7B-Instruct-v0.2,0.06,0.21,0.17,0.48,0.0,0.95,mistralai/Mistral-7B-v0.1
 🔶,Yhyu13/LMCocktail-10.7B-v1,0.1,0.44,0.23,0.51,0.0,0.97,mistralai/Mistral-7B-v0.1
 🔶,ehartford/dolphin-2.1-mistral-7b,0.08,0.1,0.2,0.4,0.0,0.92,mistralai/Mistral-7B-v0.1
+🔶,openchat/openchat-3.5-1210,0.1,0.12,0.2,0.4,0.0,0.98,mistralai/Mistral-7B-v0.1
+🔶,HuggingFaceH4/zephyr-7b-beta,0.06,0.15,0.18,0.37,0.0,0.82,mistralai/Mistral-7B-v0.1
 

data/queue.csv

@@ -1,8 +1,6 @@
 Type,Model,ref_model
-🔶 finetuned,HuggingFaceH4/zephyr-7b-beta,mistralai/Mistral-7B-v0.1
 🔶 finetuned,berkeley-nest/Starling-LM-7B-alpha,mistralai/Mistral-7B-v0.1
 🔶 finetuned,Open-Orca/Mistral-7B-OpenOrca,mistralai/Mistral-7B-v0.1
-🔶 finetuned,openchat/openchat-3.5-1210,mistralai/Mistral-7B-v0.1
 🔶 finetuned,Sao10K/Ana-v1-m7, mistralai/Mistral-7B-v0.1
 🔶 finetuned,jondurbin/bagel-dpo-7b-v0.1,mistralai/Mistral-7B-v0.1
 🔶 finetuned,rwitz/go-bruins-v2,mistralai/Mistral-7B-v0.1