From 80a3f6d4f6f3323fd147195c606e1464ee707c13 Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Thu, 9 May 2024 11:57:41 -0700 Subject: [PATCH] updated deepseek-chat yaml --- _data/edit_leaderboard.yml | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) diff --git a/_data/edit_leaderboard.yml b/_data/edit_leaderboard.yml index abf52403c..bd1f9c109 100644 --- a/_data/edit_leaderboard.yml +++ b/_data/edit_leaderboard.yml @@ -338,27 +338,29 @@ versions: 0.31.2-dev seconds_per_case: 42.4 total_cost: 0.0000 -- dirname: 2024-05-07-15-49-02--deepseek-chat-v2-diff-sysex-sysrem + +- dirname: 2024-05-09-18-27-40--deepseek-chat-v2-diff-reverted-and-helpful-assistant test_cases: 133 - model: deepseek-chat v2 (diff) + model: deepseek/deepseek-chat edit_format: diff - commit_hash: e9da401 - pass_rate_1: 42.9 - pass_rate_2: 55.6 - percent_cases_well_formed: 97.7 - error_outputs: 11 - num_malformed_responses: 3 - user_asks: 2 + commit_hash: 444d17d + pass_rate_1: 40.6 + pass_rate_2: 57.9 + percent_cases_well_formed: 93.2 + error_outputs: 30 + num_malformed_responses: 9 + user_asks: 3 lazy_comments: 0 syntax_errors: 2 indentation_errors: 0 exhausted_context_windows: 0 - test_timeouts: 4 + test_timeouts: 2 command: aider --model deepseek/deepseek-chat - date: 2024-05-07 - versions: 0.31.2-dev - seconds_per_case: 53.8 - total_cost: 0.0000 + date: 2024-05-09 + versions: 0.33.1-dev + seconds_per_case: 102.4 + total_cost: 0.1006 + - dirname: 2024-05-07-20-32-37--qwen1.5-110b-chat-whole test_cases: 133 model: qwen1.5-110b-chat