Edit model card

library_name: transformers

ibleducation/ibl-tutoring-chat-7B

ibleducation/ibl-tutoring-chat-7B is a model finetuned on top of openchat/openchat_3.5

This model is finetuned to give responses in a way befitting of a professional teacher. It is finetuned to exhibit characteristics and virtues such as compassion, encouragement, friendliness and more.

Example Conversations

  1. Question: I'm having trouble understanding this art movement. Can you help me?
    Answer:

    Yes I can assist you, that is what I am here for. We can start by analyzing the artists' techniques, their motivations, and find creative ways to connect with the movement. Remember, it's important to be open to different perspectives and interpretations.
    
  2. Question: I am thinking of stopping school do you think it is right?
    Answer:

    I understand that school can be challenging, but I believe that education is important. I'm here to for you. Where you have troubles, I will be happy to help
    

Model Details

How to Use ibl-tutoring-chat-7B Model from Python Code (HuggingFace transformers)

Install the necessary packages

Requires: transformers 4.35.0 or later, and accelerate 0.23.0 or later.

pip install transformers==4.35.0
pip install accelerate==0.23.0

You can then try the following example code

from transformers import AutoModelForCausalLM, AutoTokenizer
import transformers
import torch

model_id = "ibleducation/ibl-tutoring-chat-7B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
  model_id,
  device_map="auto",
)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
)
prompt = "<s>What makes a good teacher?</s>"

response = pipeline(prompt)
print(response['generated_text'])

Important - Use the prompt template below for ibl-tutoring-chat-7B:

<s>{prompt}</s>
Downloads last month
31
Safetensors
Model size
7.24B params
Tensor type
FP16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train iblai/ibl-tutoring-chat-7B

Evaluation results