Document model change

jncraton · Feb 14, 2025 · c2cca4f · c2cca4f
1 parent 2d013b5
commit c2cca4f
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 4 deletions.
diff --git a/changelog.md b/changelog.md
@@ -1,5 +1,11 @@
 # Changelog
 
+## 1.0
+
+### Changed
+
+- Changed default models
+
 ## 0.24 - 2024-02-14
 
 ### Changed

diff --git a/readme.md b/readme.md
@@ -149,10 +149,10 @@ Here are the current default models used by the package for a supplied `max_ram`
 | max_ram | Model Name            | Parameters (B)
 | ------- | --------------------- | --------------
 | 0.5     | LaMini-Flan-T5-248M   | 0.248
-| 1.0     | LaMini-Flan-T5-783M   | 0.783
-| 2.0     | LaMini-Flan-T5-783M   | 0.783
-| 4.0     | flan-alpaca-gpt4-xl   | 3.0
-| 8.0     | openchat-3.5-0106     | 7.0
+| 1.0     | Qwen2.5-0.5B-Instruct | 0.500
+| 2.0     | Llama-3.2-1B-Instruct | 1.24
+| 4.0     | Llama-3.2-3B-Instruct | 3.21
+| 10.0    | Llama-3.1-8B-Instruct | 8.03
 
 For code completions, the [CodeT5+](https://arxiv.org/abs/2305.07922) series of models are used.