metadata

license: apache-2.0

Model Card for Deita Complexity Scorer

Deita is an open-sourced project designed to facilitate Automatic Data Selection for instruction tuning in Large Language Models (LLMs).

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.

Usage

Please use the following format to score the complexity of the Instruction:

from transformers import AutoTokenizer, AutoModelForCausalLM
import numpy as np
from scipy.special import softmax
model_name = "hkust-nlp/Deita-Complexity-Scorer"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)


def infer_complexity(model, tokenizer, input_text):
    complexity_template = ("You are a helpful assistant. Please identify the complexity score of the following user query. \n##Query: {instruction}  \n##Complexity: ")
    user_input = complexity_template.format(instruction=input_text)
    input_ids = tokenizer.encode(user_input, return_tensors="pt")
    max_length = 512
    outputs = model.generate(input_ids, max_length=512, num_return_sequences=1, return_dict_in_generate=True, output_scores=True)
    logprobs_list = outputs.scores[0][0]
    score_logits = []
    id2score = {
        29896: "1",
        29906: "2",
        29941: "3",
        29946: "4",
        29945: "5",
        29953: "6"
    }
    score_template = np.array([1,2,3,4,5,6])
    for k in id2score:
        score_logits.append(logprobs_list[k])
    score_logits = np.array(score_logits)
    score_npy = softmax(score_logits, axis=0)
    score_npy = score_npy * score_template

    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)

print(complexity_score)