From b8bb33fe25bc55b326ae89f4aa20b604874b4ddc Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Mon, 17 Jun 2024 11:44:44 -0700 Subject: [PATCH] copy --- website/_data/edit_leaderboard.yml | 2 +- website/docs/leaderboards/index.md | 6 +++--- website/docs/llms.md | 2 +- website/docs/llms/deepseek.md | 10 +++++----- 4 files changed, 10 insertions(+), 10 deletions(-) diff --git a/website/_data/edit_leaderboard.yml b/website/_data/edit_leaderboard.yml index 379832540..82119110a 100644 --- a/website/_data/edit_leaderboard.yml +++ b/website/_data/edit_leaderboard.yml @@ -46,7 +46,7 @@ - dirname: 2024-06-17-14-45-54--deepseek-coder2-whole test_cases: 133 - model: Deepseek Coder V2 + model: DeepSeek Coder V2 edit_format: whole commit_hash: ca8672b pass_rate_1: 63.9 diff --git a/website/docs/leaderboards/index.md b/website/docs/leaderboards/index.md index de1221cc2..4e3a2a59a 100644 --- a/website/docs/leaderboards/index.md +++ b/website/docs/leaderboards/index.md @@ -16,13 +16,13 @@ While [aider can connect to almost any LLM](/docs/llms.html), it works best with models that score well on the benchmarks. -## Deepseek Coder V2 beats GPT-4o, Opus +## DeepSeek Coder V2 beats GPT-4o, Opus The new -[Deepseek Coder V2](https://aider.chat/docs/llms/deepseek.html) +[DeepSeek Coder V2](https://aider.chat/docs/llms/deepseek.html) model is now atop aider's code editing leaderboard! -It's worth noting that Deepseek Coder V2 is only capable of using aider's "whole" edit format. +It's worth noting that DeepSeek Coder V2 is only capable of using aider's "whole" edit format. This means it returns a modified full copy of each file when it makes changes. Most other strong models are able to use aider's "diff" editing format, which allows them to return diffs of edits -- saving time and token costs. diff --git a/website/docs/llms.md b/website/docs/llms.md index 0b6474cff..aecb49f27 100644 --- a/website/docs/llms.md +++ b/website/docs/llms.md @@ -23,7 +23,7 @@ as they are the very best models for editing code. Aider works with a number of **free** API providers: -- The [Deepseek Coder V2](/docs/llms/deepseek.html) model gets the top score on aider's code editing benchmark. Deepseek currently offers 5M free tokens of API usage. +- The [DeepSeek Coder V2](/docs/llms/deepseek.html) model gets the top score on aider's code editing benchmark. DeepSeek currently offers 5M free tokens of API usage. - Google's [Gemini 1.5 Pro](/docs/llms/gemini.html) is the most capable free model to use with aider, with code editing capabilities similar to GPT-3.5. - You can use [Llama 3 70B on Groq](/docs/llms/groq.html) which is comparable to GPT-3.5 in code editing performance. diff --git a/website/docs/llms/deepseek.md b/website/docs/llms/deepseek.md index de9cfdbf0..7ff93ca88 100644 --- a/website/docs/llms/deepseek.md +++ b/website/docs/llms/deepseek.md @@ -3,11 +3,11 @@ parent: Connecting to LLMs nav_order: 500 --- -# Deepseek +# DeepSeek -Aider can connect to the Deepseek.com API. -The Deepseek Coder V2 model gets the top score on aider's code editing benchmark. -Deepseek appears to grant 5M tokens of free API usage to new accounts. +Aider can connect to the DeepSeek.com API. +The DeepSeek Coder V2 model gets the top score on aider's code editing benchmark. +DeepSeek appears to grant 5M tokens of free API usage to new accounts. ``` pip install aider-chat @@ -15,7 +15,7 @@ pip install aider-chat export DEEPSEEK_API_KEY= # Mac/Linux setx DEEPSEEK_API_KEY # Windows -# Use Deepseek Coder V2 +# Use DeepSeek Coder V2 aider --model deepseek/deepseek-coder ```