From 9c13e8410984ae80ef0e426ef816e1b8d71211b1 Mon Sep 17 00:00:00 2001 From: Orion Weller Date: Wed, 21 Aug 2024 03:03:03 +0000 Subject: [PATCH] Automated Leaderboard Update --- all_data_tasks/11/default.jsonl | 2 +- all_data_tasks/12/default.jsonl | 2 +- boards_data/zh/data_overall/default.jsonl | 2 +- boards_data/zh/data_tasks/Reranking/default.jsonl | 2 +- boards_data/zh/data_tasks/Retrieval/default.jsonl | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) diff --git a/all_data_tasks/11/default.jsonl b/all_data_tasks/11/default.jsonl index 524d2eb3..bf81d727 100644 --- a/all_data_tasks/11/default.jsonl +++ b/all_data_tasks/11/default.jsonl @@ -79,4 +79,4 @@ {"index":166,"Rank":79,"Model":"SONAR<\/a>","Model Size (Million Parameters)":"","Memory Usage (GB, fp32)":"","Average":32.84,"CMedQAv1":34.31,"CMedQAv2":35.88,"MMarcoReranking":5.83,"T2Reranking":55.35} {"index":295,"Rank":80,"Model":"ALL_862873<\/a>","Model Size (Million Parameters)":118,"Memory Usage (GB, fp32)":0.44,"Average":25.86,"CMedQAv1":19.72,"CMedQAv2":22.48,"MMarcoReranking":1.17,"T2Reranking":60.05} {"index":160,"Rank":208,"Model":"sft-bge-small<\/a>","Model Size (Million Parameters)":24,"Memory Usage (GB, fp32)":0.09,"Average":"","CMedQAv1":"","CMedQAv2":"","MMarcoReranking":20.86,"T2Reranking":66.06} -{"index":167,"Rank":212,"Model":"XYZ-embedding-zh<\/a>","Model Size (Million Parameters)":326,"Memory Usage (GB, fp32)":1.21,"Average":"","CMedQAv1":"","CMedQAv2":"","MMarcoReranking":35.3,"T2Reranking":69.07} +{"index":167,"Rank":212,"Model":"XYZ-embedding-zh<\/a>","Model Size (Million Parameters)":"","Memory Usage (GB, fp32)":"","Average":"","CMedQAv1":"","CMedQAv2":"","MMarcoReranking":35.3,"T2Reranking":69.07} diff --git a/all_data_tasks/12/default.jsonl b/all_data_tasks/12/default.jsonl index a07a5aec..63aaba91 100644 --- a/all_data_tasks/12/default.jsonl +++ b/all_data_tasks/12/default.jsonl @@ -1,5 +1,5 @@ {"index":75,"Rank":1,"Model":"Zhihui_LLM_Embedding<\/a>","Model Size (Million Parameters)":7069,"Memory Usage (GB, fp32)":26.33,"Average":76.74,"CmedqaRetrieval":48.69,"CovidRetrieval":84.39,"DuRetrieval":91.34,"EcomRetrieval":71.96,"MedicalRetrieval":65.19,"MMarcoRetrieval":84.77,"T2Retrieval":88.3,"VideoRetrieval":79.31} -{"index":167,"Rank":2,"Model":"XYZ-embedding-zh<\/a>","Model Size (Million Parameters)":326,"Memory Usage (GB, fp32)":1.21,"Average":76.56,"CmedqaRetrieval":47.9,"CovidRetrieval":88.24,"DuRetrieval":90.79,"EcomRetrieval":69.72,"MedicalRetrieval":67.42,"MMarcoRetrieval":82.48,"T2Retrieval":85.93,"VideoRetrieval":80.03} +{"index":167,"Rank":2,"Model":"XYZ-embedding-zh<\/a>","Model Size (Million Parameters)":"","Memory Usage (GB, fp32)":"","Average":76.56,"CmedqaRetrieval":47.9,"CovidRetrieval":88.24,"DuRetrieval":90.79,"EcomRetrieval":69.72,"MedicalRetrieval":67.42,"MMarcoRetrieval":82.48,"T2Retrieval":85.93,"VideoRetrieval":80.03} {"index":213,"Rank":3,"Model":"xiaobu-embedding-v2<\/a>","Model Size (Million Parameters)":326,"Memory Usage (GB, fp32)":1.21,"Average":76.5,"CmedqaRetrieval":47.14,"CovidRetrieval":89.4,"DuRetrieval":89.44,"EcomRetrieval":70.5,"MedicalRetrieval":68.19,"MMarcoRetrieval":82.19,"T2Retrieval":85.01,"VideoRetrieval":80.09} {"index":176,"Rank":4,"Model":"zpoint_large_embedding_zh<\/a>","Model Size (Million Parameters)":326,"Memory Usage (GB, fp32)":1.21,"Average":76.36,"CmedqaRetrieval":47.16,"CovidRetrieval":89.14,"DuRetrieval":89.23,"EcomRetrieval":70.74,"MedicalRetrieval":68.14,"MMarcoRetrieval":82.38,"T2Retrieval":83.81,"VideoRetrieval":80.26} {"index":17,"Rank":5,"Model":"gte-Qwen2-7B-instruct<\/a>","Model Size (Million Parameters)":7613,"Memory Usage (GB, fp32)":28.36,"Average":76.03,"CmedqaRetrieval":48.69,"CovidRetrieval":83.65,"DuRetrieval":87.44,"EcomRetrieval":71.15,"MedicalRetrieval":65.59,"MMarcoRetrieval":85.16,"T2Retrieval":87.73,"VideoRetrieval":78.84} diff --git a/boards_data/zh/data_overall/default.jsonl b/boards_data/zh/data_overall/default.jsonl index 96fbdd0a..cafae3b0 100644 --- a/boards_data/zh/data_overall/default.jsonl +++ b/boards_data/zh/data_overall/default.jsonl @@ -181,7 +181,7 @@ {"index":163,"Rank":198,"Model":"stella_en_1.5B_v5<\/a>","Model Size (Million Parameters)":1543,"Memory Usage (GB, fp32)":5.75,"Embedding Dimensions":8192,"Max Tokens":131072,"Average (35 datasets)":"","Classification Average (9 datasets)":"","Clustering Average (4 datasets)":"","PairClassification Average (2 datasets)":"","Reranking Average (4 datasets)":"","Retrieval Average (8 datasets)":"","STS Average (8 datasets)":""} {"index":164,"Rank":199,"Model":"stella_en_400M_v5<\/a>","Model Size (Million Parameters)":435,"Memory Usage (GB, fp32)":1.62,"Embedding Dimensions":8192,"Max Tokens":8192,"Average (35 datasets)":"","Classification Average (9 datasets)":"","Clustering Average (4 datasets)":"","PairClassification Average (2 datasets)":"","Reranking Average (4 datasets)":"","Retrieval Average (8 datasets)":"","STS Average (8 datasets)":""} {"index":165,"Rank":200,"Model":"e5-base-4k<\/a>","Model Size (Million Parameters)":110,"Memory Usage (GB, fp32)":0.41,"Embedding Dimensions":768,"Max Tokens":512,"Average (35 datasets)":"","Classification Average (9 datasets)":"","Clustering Average (4 datasets)":"","PairClassification Average (2 datasets)":"","Reranking Average (4 datasets)":"","Retrieval Average (8 datasets)":"","STS Average (8 datasets)":""} -{"index":167,"Rank":201,"Model":"XYZ-embedding-zh<\/a>","Model Size (Million Parameters)":326,"Memory Usage (GB, fp32)":1.21,"Embedding Dimensions":1792,"Max Tokens":512,"Average (35 datasets)":"","Classification Average (9 datasets)":"","Clustering Average (4 datasets)":"","PairClassification Average (2 datasets)":"","Reranking Average (4 datasets)":"","Retrieval Average (8 datasets)":76.56,"STS Average (8 datasets)":""} +{"index":167,"Rank":201,"Model":"XYZ-embedding-zh<\/a>","Model Size (Million Parameters)":"","Memory Usage (GB, fp32)":"","Embedding Dimensions":"","Max Tokens":"","Average (35 datasets)":"","Classification Average (9 datasets)":"","Clustering Average (4 datasets)":"","PairClassification Average (2 datasets)":"","Reranking Average (4 datasets)":"","Retrieval Average (8 datasets)":76.56,"STS Average (8 datasets)":""} {"index":168,"Rank":202,"Model":"flaubert_base_cased<\/a>","Model Size (Million Parameters)":138,"Memory Usage (GB, fp32)":0.51,"Embedding Dimensions":768,"Max Tokens":512,"Average (35 datasets)":"","Classification Average (9 datasets)":"","Clustering Average (4 datasets)":"","PairClassification Average (2 datasets)":"","Reranking Average (4 datasets)":"","Retrieval Average (8 datasets)":"","STS Average (8 datasets)":""} {"index":169,"Rank":203,"Model":"flaubert_base_uncased<\/a>","Model Size (Million Parameters)":138,"Memory Usage (GB, fp32)":0.51,"Embedding Dimensions":768,"Max Tokens":512,"Average (35 datasets)":"","Classification Average (9 datasets)":"","Clustering Average (4 datasets)":"","PairClassification Average (2 datasets)":"","Reranking Average (4 datasets)":"","Retrieval Average (8 datasets)":"","STS Average (8 datasets)":""} {"index":170,"Rank":204,"Model":"flaubert_large_cased<\/a>","Model Size (Million Parameters)":372,"Memory Usage (GB, fp32)":1.39,"Embedding Dimensions":1024,"Max Tokens":512,"Average (35 datasets)":"","Classification Average (9 datasets)":"","Clustering Average (4 datasets)":"","PairClassification Average (2 datasets)":"","Reranking Average (4 datasets)":"","Retrieval Average (8 datasets)":"","STS Average (8 datasets)":""} diff --git a/boards_data/zh/data_tasks/Reranking/default.jsonl b/boards_data/zh/data_tasks/Reranking/default.jsonl index 524d2eb3..bf81d727 100644 --- a/boards_data/zh/data_tasks/Reranking/default.jsonl +++ b/boards_data/zh/data_tasks/Reranking/default.jsonl @@ -79,4 +79,4 @@ {"index":166,"Rank":79,"Model":"SONAR<\/a>","Model Size (Million Parameters)":"","Memory Usage (GB, fp32)":"","Average":32.84,"CMedQAv1":34.31,"CMedQAv2":35.88,"MMarcoReranking":5.83,"T2Reranking":55.35} {"index":295,"Rank":80,"Model":"ALL_862873<\/a>","Model Size (Million Parameters)":118,"Memory Usage (GB, fp32)":0.44,"Average":25.86,"CMedQAv1":19.72,"CMedQAv2":22.48,"MMarcoReranking":1.17,"T2Reranking":60.05} {"index":160,"Rank":208,"Model":"sft-bge-small<\/a>","Model Size (Million Parameters)":24,"Memory Usage (GB, fp32)":0.09,"Average":"","CMedQAv1":"","CMedQAv2":"","MMarcoReranking":20.86,"T2Reranking":66.06} -{"index":167,"Rank":212,"Model":"XYZ-embedding-zh<\/a>","Model Size (Million Parameters)":326,"Memory Usage (GB, fp32)":1.21,"Average":"","CMedQAv1":"","CMedQAv2":"","MMarcoReranking":35.3,"T2Reranking":69.07} +{"index":167,"Rank":212,"Model":"XYZ-embedding-zh<\/a>","Model Size (Million Parameters)":"","Memory Usage (GB, fp32)":"","Average":"","CMedQAv1":"","CMedQAv2":"","MMarcoReranking":35.3,"T2Reranking":69.07} diff --git a/boards_data/zh/data_tasks/Retrieval/default.jsonl b/boards_data/zh/data_tasks/Retrieval/default.jsonl index a07a5aec..63aaba91 100644 --- a/boards_data/zh/data_tasks/Retrieval/default.jsonl +++ b/boards_data/zh/data_tasks/Retrieval/default.jsonl @@ -1,5 +1,5 @@ {"index":75,"Rank":1,"Model":"Zhihui_LLM_Embedding<\/a>","Model Size (Million Parameters)":7069,"Memory Usage (GB, fp32)":26.33,"Average":76.74,"CmedqaRetrieval":48.69,"CovidRetrieval":84.39,"DuRetrieval":91.34,"EcomRetrieval":71.96,"MedicalRetrieval":65.19,"MMarcoRetrieval":84.77,"T2Retrieval":88.3,"VideoRetrieval":79.31} -{"index":167,"Rank":2,"Model":"XYZ-embedding-zh<\/a>","Model Size (Million Parameters)":326,"Memory Usage (GB, fp32)":1.21,"Average":76.56,"CmedqaRetrieval":47.9,"CovidRetrieval":88.24,"DuRetrieval":90.79,"EcomRetrieval":69.72,"MedicalRetrieval":67.42,"MMarcoRetrieval":82.48,"T2Retrieval":85.93,"VideoRetrieval":80.03} +{"index":167,"Rank":2,"Model":"XYZ-embedding-zh<\/a>","Model Size (Million Parameters)":"","Memory Usage (GB, fp32)":"","Average":76.56,"CmedqaRetrieval":47.9,"CovidRetrieval":88.24,"DuRetrieval":90.79,"EcomRetrieval":69.72,"MedicalRetrieval":67.42,"MMarcoRetrieval":82.48,"T2Retrieval":85.93,"VideoRetrieval":80.03} {"index":213,"Rank":3,"Model":"xiaobu-embedding-v2<\/a>","Model Size (Million Parameters)":326,"Memory Usage (GB, fp32)":1.21,"Average":76.5,"CmedqaRetrieval":47.14,"CovidRetrieval":89.4,"DuRetrieval":89.44,"EcomRetrieval":70.5,"MedicalRetrieval":68.19,"MMarcoRetrieval":82.19,"T2Retrieval":85.01,"VideoRetrieval":80.09} {"index":176,"Rank":4,"Model":"zpoint_large_embedding_zh<\/a>","Model Size (Million Parameters)":326,"Memory Usage (GB, fp32)":1.21,"Average":76.36,"CmedqaRetrieval":47.16,"CovidRetrieval":89.14,"DuRetrieval":89.23,"EcomRetrieval":70.74,"MedicalRetrieval":68.14,"MMarcoRetrieval":82.38,"T2Retrieval":83.81,"VideoRetrieval":80.26} {"index":17,"Rank":5,"Model":"gte-Qwen2-7B-instruct<\/a>","Model Size (Million Parameters)":7613,"Memory Usage (GB, fp32)":28.36,"Average":76.03,"CmedqaRetrieval":48.69,"CovidRetrieval":83.65,"DuRetrieval":87.44,"EcomRetrieval":71.15,"MedicalRetrieval":65.59,"MMarcoRetrieval":85.16,"T2Retrieval":87.73,"VideoRetrieval":78.84}