metadata
license: apache-2.0
language:
- en
base_model:
- distilbert/distilbert-base-uncased
pipeline_tag: text-ranking
Model Card for Model ID
This is a text Reranker model to score if a text is kindergarten-teacher style.
Model Details
Model Description
- 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
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
[Training Dataset Card](to be add) Training process can be found on Github.
Contact
For any questions, please contact the author [email protected]