From 73de0ea8beb15fc373c7bb722900bcfd3545e115 Mon Sep 17 00:00:00 2001
From: Paul Gauthier <aider@paulg.org>
Date: Sat, 23 Nov 2024 20:18:19 -0800
Subject: [PATCH] copy

---
 aider/website/_data/quant.yml                 | 25 ++++++++++++++++++-
 .../website/_posts/2024-11-21-quantization.md |  1 -
 2 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/aider/website/_data/quant.yml b/aider/website/_data/quant.yml
index ac177aa4f..3445144e9 100644
--- a/aider/website/_data/quant.yml
+++ b/aider/website/_data/quant.yml
@@ -181,4 +181,27 @@
   date: 2024-11-24
   versions: 0.64.2.dev
   seconds_per_case: 17.5
-  total_cost: 0.0000
\ No newline at end of file
+  total_cost: 0.0000
+
+- dirname: 2024-11-24-04-12-58--fireworks-qwen-diff
+  test_cases: 133
+  model: Fireworks (unknown quant)
+  edit_format: diff
+  commit_hash: 757eac0
+  pass_rate_1: 57.9
+  pass_rate_2: 72.2
+  percent_cases_well_formed: 94.0
+  error_outputs: 23
+  num_malformed_responses: 19
+  num_with_malformed_responses: 8
+  user_asks: 8
+  lazy_comments: 0
+  syntax_errors: 6
+  indentation_errors: 0
+  exhausted_context_windows: 4
+  test_timeouts: 1
+  command: aider --model fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct
+  date: 2024-11-24
+  versions: 0.64.2.dev
+  seconds_per_case: 10.4
+  total_cost: 0.5759
\ 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 c059a892f..6f5104b94 100644
--- a/aider/website/_posts/2024-11-21-quantization.md
+++ b/aider/website/_posts/2024-11-21-quantization.md
@@ -28,7 +28,6 @@ The graph above compares different versions of the Qwen 2.5 Coder 32B Instruct m
 served both locally and from cloud providers.
 
 - The [HuggingFace BF16 weights](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) served via [glhf.chat](https://glhf.chat).
-- Hyperbolic labs API for [qwen2-5-coder-32b-instruct](https://app.hyperbolic.xyz/models/qwen2-5-coder-32b-instruct), which is using BF16. This result is probably within the expected variance of the HF result.
 - [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).