current eval and queue

data/code_eval_board.csv

@@ -13,4 +13,9 @@ T,Models,ARC,HellaSwag,MMLU,TruthfulQA,Winogrande,GSM8K,Reference Model
 🔶,teknium/OpenHermes-2.5-Mistral-7B,0.07,0.13,0.23,0.39,0.0,0.96,mistralai/Mistral-7B-v0.1
 🔶,microsoft/Orca-2-7b,0.88,0.8,0.77,0.91,0.0,1.0,mistralai/Mistral-7B-v0.1
 🔶,WizardLM/WizardMath-7B-V1.1,0.1,0.11,0.21,0.4,0.0,0.99,mistralai/Mistral-7B-v0.1
+🔶,01-ai/Yi-6B-200K,0.19,0.3,0.3,0.6,0.93,mistralai/Mistral-7B-v0.1
+🔶,Intel/neural-chat-7b-v3-3,0.06,0.15,0.18,0.47,0.0,0.98,mistralai/Mistral-7B-v0.1
+🔶,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
 

data/queue.csv

@@ -1,14 +1,10 @@
 Type,Model,ref_model
-🔶 finetuned,Intel/neural-chat-7b-v3-3,mistralai/Mistral-7B-v0.1
-🔶 finetuned,mistralai/Mistral-7B-Instruct-v0.2,mistralai/Mistral-7B-v0.1
-🔶 finetuned,ehartford/dolphin-2.1-mistral-7b,mistralai/Mistral-7B-v0.1
 🔶 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,01-ai/Yi-6B-200K,mistralai/Mistral-7B-v0.1
-🔶 finetuned,Yhyu13/LMCocktail-10.7B-v1,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
-🔶 finetuned,chargoddard/loyal-piano-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
+🔶 finetuned,EmbeddedLLM/Mistral-7B-Merge-14-v0.3,mistralai/Mistral-7B-v0.1