metadata
base_model: Qwen/Qwen1.5-1.8B
library_name: peft
license: apache-2.0
language:
- en
pipeline_tag: text2text-generation
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
- 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
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
[Training Dataset Card](to be add) Training process can be found on Github.
Contact
For any questions, please contact the author yinmiao025@gmail.com