From 3aadc12f044ede61fd6aaed7a96629cdc77c5ba1 Mon Sep 17 00:00:00 2001
From: Colin <colin@uninsane.org>
Date: Sun, 3 Nov 2024 12:16:27 +0000
Subject: [PATCH] services: ollama: remove some LLM models which ive found to
 not be useful

---
 modules/services/ollama.nix | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/modules/services/ollama.nix b/modules/services/ollama.nix
index 850e04b3b..502cb8b25 100644
--- a/modules/services/ollama.nix
+++ b/modules/services/ollama.nix
@@ -24,7 +24,7 @@ let
       codestral-22b
       # deepseek-coder-7b  # subpar to deepseek-coder-v2 in nearly every way
       deepseek-coder-v2-16b  # GREAT balance between speed and code quality. code is superior to qwen2_5 in some ways, and inferior in others
-      deepseek-coder-v2-16b-lite-instruct-q5_1  # higher-res version of default 16b (so, better answers?)
+      # deepseek-coder-v2-16b-lite-instruct-q5_1  # higher-res version of default 16b (but in practice, is more rambly and less correct)
       # falcon2-11b  # code examples are lacking
       # gemma2-9b  # fast, but not great for code
       # glm4-9b  # it generates invalid code
@@ -37,17 +37,17 @@ let
       # mistral-nemo-12b  # it generates invalid code
       mistral-small-22b  # quality comparable to qwen2_5
       # mistral-large-123b  # times out launch on desko
-      mixtral-8x7b  # generates valid, if sparse, code
+      # mixtral-8x7b  # generates valid, if sparse, code; only for the most popular languages
       # phi3_5-3b  # generates invalid code
       # qwen2_5-7b   # notably less quality than 32b (i.e. generates invalid code)
       qwen2_5-14b  # *almost* same quality to 32b variant, but faster
-      qwen2_5-32b-instruct-q2_K  # lower-res version of default 32b (so, faster?)
+      # qwen2_5-32b-instruct-q2_K  # lower-res version of default 32b (so, slightly faster, but generates invalid code where the full res generates valid code)
       qwen2_5-32b  # generates 3~5 words/sec, but notably more accurate than coder-7b
       # qwen2_5-coder-7b  # fast, and concise, but generates invalid code
       # solar-pro-22b  # generates invalid code
       # starcoder2-15b-instruct  # it gets stuck
       # wizardlm2-7b  # generates invalid code
-      yi-coder-9b  # subpar to qwen2-14b, but it's still useful
+      # yi-coder-9b  # subpar to qwen2-14b, but it's still useful
     ];
   };
   models = "${modelSources}/share/ollama/models";