Qwen-KinderChatbot-LoRA

Model Card for Model ID

This is a kindergarten-teacher-style text-to-text generation model fined tuned on Qwen1.5-1.8B. It gives answers to any input question like a gentle and warm kindergarten teacher.

Model Details

Model Description

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

• Developed by: Miao025
• Model type: Causal Language Model (decoder-only)
• Model size: 1.8B params
• Language(s) (NLP): English
• License: apache-2.0
• Finetuned from model [optional]: Qwen/Qwen1.5-1.8B
• Demo: A fine-tuned AI KinderChatbot based on this sft 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
import torch

# Load tokenizer and fine-tuned model (Note that you can also download the models and load with local path.)
tokenizer_sft = AutoTokenizer.from_pretrained("Miao025/Qwen-KinderChatbot-LoRA")
sft_model = AutoModelForCausalLM.from_pretrained("Miao025/Qwen-KinderChatbot-LoRA").to("cuda") # Recommend to use gpu as this is a large model

# Prepare prompt
prompt = "Why do we need to brush our teeth?"
inputs = tokenizer_sft(prompt, return_tensors="pt", truncation=True).to("cuda")

# Generate a response
output = sft_model.generate(**inputs)

# Decode the result
response = tokenizer_sft.decode(output[0], skip_special_tokens=True)

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]