Hugging Face's logo

iblai
/
ibl-tutoring-chat-7B

Text Generation
Transformers
Safetensors
mistral
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
ibl-tutoring-chat-7B / README.md
Joetib's picture
Joetib
Update README.md
64508fb
preview code
|
raw
history blame contribute delete
3.81 kB
metadata
metrics:
  - rouge
  - bleu
  - bleurt
model-index:
  - name: ibleducation/ibl-tutoring-chat-7B
    results:
      - task:
          name: truthfulqa_gen
          type: text-generation
        dataset:
          type: truthful_qa
          name: Truthful QA
        metrics:
          - type: bleurt
            name: bleurt_max
            value: -0.5572
          - type: bleurt
            name: bleurt_acc
            value: 0.4321
          - type: bleurt
            name: bleurt_diff
            value: -0.0725
          - type: bleu
            name: bleu_max
            value: 22.5935
          - type: bleu
            name: bleu_acc
            value: 0.3758
          - type: bleu
            name: bleu_diff
            value: -2.5541
          - type: rouge
            name: rouge1_max
            value: 50.0851
          - type: rouge
            name: rouge1_acc
            value: 0.3978
          - type: rouge
            name: rouge1_diff
            value: -3.5142
          - type: rouge
            name: rouge2_max
            value: 34.7473
          - type: rouge
            name: rouge2_acc
            value: 0.339
          - type: rouge
            name: rouge2_diff
            value: -4.5082
          - type: rouge
            name: rougeL_max
            value: 46.1054
          - type: rouge
            name: rougeL_acc
            value: 0.3745
          - type: rouge
            name: rougeL_diff
            value: -4.0046
datasets:
  - ibleducation/ibl-best-practices-instructor-dataset

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>