Fine tune x2

Original version was fine tuned on the 18k Python data set. The most recent update (as 6/5/2024) was fine tuned further on an additional data set (23k entries).

README.md

@@ -10,6 +10,11 @@ tags:
 - trl
 - sft
 base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
+datasets:
+- iamtarun/python_code_instructions_18k_alpaca
+- ajibawa-2023/Python-Code-23k-ShareGPT
+library_name: adapter-transformers
+pipeline_tag: question-answering
 ---
 
 # Uploaded  model
@@ -20,4 +25,4 @@ base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
 
 This mistral 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)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)