Update README.md

README.md

@@ -2,11 +2,26 @@
 license: apache-2.0
 ---
 
-# Deita-Quality-Scorer
+# Model Card for Deita Complexity Scorer
 
-Deita-Quality-Scorer is a tool for automatically annotating the Instruction Complexity of SFT data.
+Deita is an open-sourced project designed to facilitate **Automatic Data Selection** for instruction tuning in Large Language Models (LLMs).
 
-## Uses
+Deita Complexity Scorer is a tool for automatically annotating the Instruction Complexity of SFT data.
+
+## Model description
+
+- **Model type:** Model fine tuned to automatically annotate the Instruction Complexity
+- **Language(s) (NLP):** Primarily English
+- **Finetuned from model:** Llama-1-13b-hf
+
+### Model Sources
+
+- **Repository:** https://github.com/hkust-nlp/deita
+- **Model Family:** Other models and the dataset are found in the [Deita collection](https://huggingface.co/collections/hkust-nlp/deita-6569c198c174808d94cf5bd4).
+
+## Usage
+
+Please use the following format
 
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
@@ -43,6 +58,7 @@ def infer_complexity(model, tokenizer, input_text):
 	score_npy = np.sum(score_npy, axis=0)
 	return score_npy
 
+# example input
 input_text = "write a performance review for a junior data scientist"
 complexity_score = infer_complexity(model, tokenizer, input_text)