From 757eac05791ed9f19abbc368a7846739d0ed16bb Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Sat, 23 Nov 2024 18:39:20 -0800 Subject: [PATCH] copy --- aider/website/_data/quant.yml | 23 +++++++++++++++++++ .../website/_posts/2024-11-21-quantization.md | 1 + 2 files changed, 24 insertions(+) diff --git a/aider/website/_data/quant.yml b/aider/website/_data/quant.yml index cb5906334..ac177aa4f 100644 --- a/aider/website/_data/quant.yml +++ b/aider/website/_data/quant.yml @@ -158,4 +158,27 @@ date: 2024-11-23 versions: 0.64.2.dev seconds_per_case: 35.7 + total_cost: 0.0000 + +- dirname: 2024-11-24-02-23-32--deepinfra-qwen-diff + test_cases: 133 + model: Deepinfra (BF16) + edit_format: diff + commit_hash: bb78e2f + pass_rate_1: 58.6 + pass_rate_2: 72.2 + percent_cases_well_formed: 94.7 + error_outputs: 15 + num_malformed_responses: 13 + num_with_malformed_responses: 7 + user_asks: 3 + lazy_comments: 0 + syntax_errors: 0 + indentation_errors: 0 + exhausted_context_windows: 2 + test_timeouts: 3 + command: aider --model deepinfra/Qwen/Qwen2.5-Coder-32B-Instruct + date: 2024-11-24 + versions: 0.64.2.dev + seconds_per_case: 17.5 total_cost: 0.0000 \ No newline at end of file diff --git a/aider/website/_posts/2024-11-21-quantization.md b/aider/website/_posts/2024-11-21-quantization.md index 3d9372194..c059a892f 100644 --- a/aider/website/_posts/2024-11-21-quantization.md +++ b/aider/website/_posts/2024-11-21-quantization.md @@ -32,6 +32,7 @@ served both locally and from cloud providers. - [4bit and 8bit quants for mlx](https://t.co/cwX3DYX35D). - The results from [OpenRouter's mix of providers](https://openrouter.ai/qwen/qwen-2.5-coder-32b-instruct/providers) which serve the model with different levels of quantization. - Ollama locally serving different quantizations from the [Ollama model library](https://ollama.com/library/qwen2.5-coder:32b-instruct-q4_K_M). +- Other API providers. The best version of the model rivals GPT-4o, while the worst performer is more like GPT-4 level.