current evals

data/code_eval_board.csv

@@ -20,4 +20,6 @@ T,Models,ARC,HellaSwag,MMLU,TruthfulQA,Winogrande,GSM8K,Reference Model
 🔶,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
+🔶,berkeley-nest/Starling-LM-7B-alpha,0.1,0.13,0.19,0.39,0.0,0.97,mistralai/Mistral-7B-v0.1
+🔶,Sao10K/Ana-v1-m7,0.11,0.12,0.19,0.41,0.0,0.84,mistralai/Mistral-7B-v0.1
 

data/queue.csv

@@ -1,7 +1,5 @@
 Type,Model,ref_model
-🔶 finetuned,berkeley-nest/Starling-LM-7B-alpha,mistralai/Mistral-7B-v0.1
 🔶 finetuned,Open-Orca/Mistral-7B-OpenOrca,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
 🔶 finetuned,chargoddard/loyal-piano-m7,mistralai/Mistral-7B-v0.1