dushj98
/

action-gemma-2-test-v2

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

dushj98 commited on Sep 26

Commit

f6c00f7

•

1 Parent(s): 7c9c7a4

Update README.md

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ tags:
 - trl
 ---
-# Uploaded  model
 - **Developed by:** dushj98
 - **License:** apache-2.0
@@ -20,3 +20,5 @@ tags:
 This gemma2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 - trl
 ---
+# ActionGemma2 v2
 - **Developed by:** dushj98
 - **License:** apache-2.0
 This gemma2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+This version of the model was fine-tuned for a full epoch whereas [ActionGemma2 v1](https://huggingface.co/dushj98/action-gemma-2-v1) was only fine-tuned for 60 steps.