Update README.md

README.md

@@ -22,34 +22,43 @@ This is the repo for the GPT-4-LLM, which aims to share data generated by GPT-4
 
 **Usage and License Notices**: The data is intended and licensed for research use only. The dataset is CC BY NC 4.0 (allowing only non-commercial use) and models trained using the dataset should not be used outside of research purposes.
 
+
+- [Overview](#overview)
+- [GPT-4 Data Release](#data-release)
+- [How Good is the Data?](#how-good-is-the-data)
+- [Fine-tuning with the Data](#fine-tuning-with-the-data)
+
 ## :fire: News
 
 * **[2023.04.06]** Paper and data are released.
 
+
+
+
 ## Overview
 Large Language Models (LLMs) have shown impressive generalization capabilities such as in-context-learning and chain-of-thoughts reasoning. To enable LLMs to follow natural language instructions and complete real-world tasks, researchers have been exploring methods of instruction-tuning of LLMs. To advance the state of the art of instruction-tuning for LLMs, we present the first attempt to use GPT-4 to generate instruction-following data for LLM finetuning. 
 
 ## Data Release
 
-[`alpaca_gpt4_data.json`](./data/alpaca_gpt4_data.json) contains 52K instruction-following data generated by GPT-4 with prompts in Alpaca.
+* [`alpaca_gpt4_data.json`](./data/alpaca_gpt4_data.json) contains 52K instruction-following data generated by GPT-4 with prompts in Alpaca.
 This JSON file has the same format as Alpaca data, except the output is generated by GPT-4:
 
-- `instruction`: `str`, describes the task the model should perform. Each of the 52K instructions is unique.
-- `input`: `str`, optional context or input for the task. 
-- `output`: `str`, the answer to the instruction as generated by `GPT-4`.
+    - `instruction`: `str`, describes the task the model should perform. Each of the 52K instructions is unique.
+    - `input`: `str`, optional context or input for the task. 
+    - `output`: `str`, the answer to the instruction as generated by `GPT-4`.
 
 
-[`alpaca_gpt4_data_zh.json`](./data/alpaca_gpt4_data_zh.json) contains 52K instruction-following data generated by GPT-4 with Alpaca prompts translated into Chinese by ChatGPT. This JSON file has the same format.
+* [`alpaca_gpt4_data_zh.json`](./data/alpaca_gpt4_data_zh.json) contains 52K instruction-following data generated by GPT-4 with Alpaca prompts translated into Chinese by ChatGPT. This JSON file has the same format.
 
-[`comparision_data.json`](./data/comparision_data.json) ranked responses from three models, including GPT-4, GPT-3.5 and OPT-IML by asking GPT-4 to rate the quality.
+* [`comparision_data.json`](./data/comparision_data.json) ranked responses from three models, including GPT-4, GPT-3.5 and OPT-IML by asking GPT-4 to rate the quality.
 
-- `user_input`: `str`, prompts used for quering LLMs.
-- `completion_a`: `str`, a model completion which is ranked higher than completion_b.
-- `completion_b`: `str`, a different model completion which has a lower quality score. 
+    - `user_input`: `str`, prompts used for quering LLMs.
+    - `completion_a`: `str`, a model completion which is ranked higher than completion_b.
+    - `completion_b`: `str`, a different model completion which has a lower quality score. 
 
-[`unnatural_instruction_gpt4_data.json`](./data/unnatural_instruction_gpt4_data.json) contains 9K instruction-following data generated by GPT-4 with prompts in Unnatural Instruction. This JSON file has the same format as Alpaca data.
+* [`unnatural_instruction_gpt4_data.json`](./data/unnatural_instruction_gpt4_data.json) contains 9K instruction-following data generated by GPT-4 with prompts in Unnatural Instruction. This JSON file has the same format as Alpaca data.
 
-## How Good is the Data?
+## How Good is the Data
 
 Human evaluation was performed on model generation results using Amazon Mechanical Turk following Helpfulness, Honestness and Harmlessness criteria by [Anthropic AI](https://arxiv.org/abs/2112.00861). The results are summarized as follows:
 - Two instruction-tuned LLaMA models were compared, fine-tuned on data generated by GPT-4 and GPT-3 respectively.