reflection-tuning dataset generation (#349)

Author: rasbt

README.md

@@ -122,7 +122,8 @@ Several folders contain optional materials as a bonus for interested readers:
 - **Chapter 7:**
   - [Dataset Utilities for Finding Near Duplicates and Creating Passive Voice Entries](ch07/02_dataset-utilities)
   - [Evaluating Instruction Responses Using the OpenAI API and Ollama](ch07/03_model-evaluation)
-  - [Generating a Dataset for Instruction Finetuning](ch07/05_dataset-generation)
+  - [Generating a Dataset for Instruction Finetuning](ch07/05_dataset-generation/llama3-ollama.ipynb)
+  - [Improving a Dataset for Instruction Finetuning](ch07/05_dataset-generation/reflection-gpt4.ipynb)
   - [Generating a Preference Dataset with Llama 3.1 70B and Ollama](ch07/04_preference-tuning-with-dpo/create-preference-data-ollama.ipynb)
   - [Direct Preference Optimization (DPO) for LLM Alignment](ch07/04_preference-tuning-with-dpo/dpo-from-scratch.ipynb)
 

ch07/05_dataset-generation/README.md

@@ -1,6 +1,7 @@
-# Generating a Dataset for Instruction Finetuning
+# Generating Datasets for Instruction Finetuning
 
 This folder contains utility code that can be used for generating a dataset for instruction finetuning.
 
 - [llama3-ollama.ipynb](llama3-ollama.ipynb): A notebook that creates a synthetic instruction finetuning dataset using Llama 3 and Ollama
 
+- [reflection-gpt4.ipynb](reflection-gpt4.ipynb): A notebook that implements an instruction dataset refinement step based on reflection-tuning

ch07/05_dataset-generation/config.json

@@ -0,0 +1,4 @@
+{
+  "OPENAI_API_KEY": "sk-...",
+  "_comment": "Enter your API key from https://platform.openai.com/api-keys"
+}

ch07/05_dataset-generation/llama3-ollama.ipynb

@@ -498,7 +498,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,