dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-05-29 08:44:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

copy

Browse source
This commit is contained in:
Paul Gauthier 2024-11-22 10:56:33 -08:00
parent 6a0a97cb41
commit f06452c6c5
2 changed files with 8 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

8
aider/website/_data/quant.yml
View file

@ -1,6 +1,6 @@
- dirname: 2024-11-09-11-09-15--Qwen2.5-Coder-32B-Instruct - dirname: 2024-11-09-11-09-15--Qwen2.5-Coder-32B-Instruct
test_cases: 133 test_cases: 133
model: HuggingFace BF16 via glhf.chat model: HuggingFace BF16 via GLHF
released: 2024-11-12 released: 2024-11-12
edit_format: diff edit_format: diff
commit_hash: ec9982a commit_hash: ec9982a
@ -24,7 +24,7 @@
- dirname: 2024-11-22-14-53-26--hyperbolic-qwen25coder32binstruct - dirname: 2024-11-22-14-53-26--hyperbolic-qwen25coder32binstruct
test_cases: 133 test_cases: 133
model: Hyperbolic Qwen2.5-Coder-32B-Instruct BF16 model: Hyperbolic BF16
edit_format: diff edit_format: diff
commit_hash: f9ef161, 17aef7b-dirty commit_hash: f9ef161, 17aef7b-dirty
pass_rate_1: 57.9 pass_rate_1: 57.9
@ -47,7 +47,7 @@
- dirname: 2024-11-20-15-17-37--qwen25-32b-or-diff - dirname: 2024-11-20-15-17-37--qwen25-32b-or-diff
test_cases: 133 test_cases: 133
model: openrouter/qwen/qwen-2.5-coder-32b-instruct (mixed quants) model: OpenRouter (mixed)
edit_format: diff edit_format: diff
commit_hash: e917424 commit_hash: e917424
pass_rate_1: 49.6 pass_rate_1: 49.6
@ -70,7 +70,7 @@
- dirname: 2024-11-21-23-33-47--ollama-qwen25-coder - dirname: 2024-11-21-23-33-47--ollama-qwen25-coder
test_cases: 133 test_cases: 133
model: qwen2.5-coder:32b-instruct-q4_K_M model: Ollama Q4_K_M
edit_format: diff edit_format: diff
commit_hash: 488c88d-dirty commit_hash: 488c88d-dirty
pass_rate_1: 44.4 pass_rate_1: 44.4

7
aider/website/_posts/2024-11-21-quantization.md
View file

@ -35,6 +35,10 @@ served both locally and from cloud providers.
The best version of the model rivals GPT-4o, while the worst performer The best version of the model rivals GPT-4o, while the worst performer
is more like GPT-3.5 Turbo level. is more like GPT-3.5 Turbo level.
{: .note }
This article is being updated as new benchmark runs complete.
The original version included incorrect Ollama models.
<input type="text" id="quantSearchInput" placeholder="Search..." style="width: 100%; max-width: 800px; margin: 10px auto; padding: 8px; display: block; border: 1px solid #ddd; border-radius: 4px;"> <input type="text" id="quantSearchInput" placeholder="Search..." style="width: 100%; max-width: 800px; margin: 10px auto; padding: 8px; display: block; border: 1px solid #ddd; border-radius: 4px;">
<table style="width: 100%; max-width: 800px; margin: auto; border-collapse: collapse; box-shadow: 0 2px 4px rgba(0,0,0,0.1); font-size: 14px;"> <table style="width: 100%; max-width: 800px; margin: auto; border-collapse: collapse; box-shadow: 0 2px 4px rgba(0,0,0,0.1); font-size: 14px;">
@ -103,6 +107,3 @@ OpenRouter allows you to ignore specific providers in your
This can be effective to exclude highly quantized or otherwise This can be effective to exclude highly quantized or otherwise
undesirable providers. undesirable providers.
{: .note }
The original version of this article included incorrect Ollama models
that were not Qwen 2.5 Coder 32B Instruct.