Qwen-KinderChatbot-Reward

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

This is a text Reranker model to score if a text is kindergarten-teacher style.

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

• Developed by: Miao025
• Model type: Text Reranking
• Model size: 67M params
• Language(s) (NLP): English
• License: apache-2.0
• Finetuned from model [optional]: distilbert/distilbert-base-uncased
• Demo: A fine-tuned AI KinderChatbot using this Rerank model

Useage

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

from transformers import AutoTokenizer, AutoModelForCausalLM

# Load tokenizer and reranker model (Note that you can also download the models and load with local path.)
tokenizer_reward = AutoTokenizer.from_pretrained("Miao025/Qwen-KinderChatbot-Reward")
reward_model = AutoModelForSequenceClassification.from_pretrained("Miao025/Qwen-KinderChatbot-Reward")

# For each prompt-response pair, get the score
inputs = tokenizer_reward(prompt, response, return_tensors="pt", truncation=True)
with torch.no_grad():
    logits = reward_model(**inputs).logits
    score = torch.softmax(logits, dim=-1)[0,1].item()

Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[Training Dataset Card](to be add) Training process can be found on Github.

Contact

For any questions, please contact the author [email protected]