sometimesanotion
/

Lamarck-14B-v0.7

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

sometimesanotion commited on 13 days ago

Commit

d7b87f3

·

verified ·

1 Parent(s): acc208f

Update README.md

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -14,11 +14,13 @@ license: apache-2.0
 language:
 - en
 pipeline_tag: text-generation
 ---
-![Lamarck.webp](https://huggingface.co/sometimesanotion/Lamarck-14B-v0.7/resolve/main/Lamarck.webp)
 ---
-> [!TIP] This update pushes the merge techniques behind [sometimesanotion/Lamarck-14B-v0.6](https://huggingface.co/sometimesanotion/Lamarck-14B-v0.6) further, with notably better prose with underlying improvements in IFEVAL, MATH, and MUSR.
 Lamarck 14B v0.7:  A generalist merge focused on multi-step reasoning, prose, and multi-language ability.  It is based on components that have punched above their weight in the 14 billion parameter class.  It uses a custom toolchain to create and apply multiple sequences of complex merges:

 language:
 - en
 pipeline_tag: text-generation
+metrics:
+- accuracy
 ---
+![Lamarck.webp](https://huggingface.co/sometimesanotion/Lamarck-14B-v0.7/resolve/main/LamarckShades.webp)
 ---
+> [!TIP] This version of the model has broken the 41.0 average barrier for 14B parameter models, and as of this writing, ranks #7 among models under 70B parameters.  Given the respectable performance in the 32B range, I think Lamarck deserves his shades.  A little layer analysis in the 14B range goes a long, long way.
 Lamarck 14B v0.7:  A generalist merge focused on multi-step reasoning, prose, and multi-language ability.  It is based on components that have punched above their weight in the 14 billion parameter class.  It uses a custom toolchain to create and apply multiple sequences of complex merges: