|
--- |
|
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: |
|
```code |
|
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: |
|
```code |
|
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 |
|
|
|
- **Developed by:** [IBL Education](https://ibl.ai) |
|
- **Model type:** [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) |
|
- **Base Model:** [OpenChat 3.5](https://huggingface.co/openchat/openchat_3.5) |
|
- **Language:** English |
|
- **Finetuned from weights:** [OpenChat 3.5](https://huggingface.co/openchat/openchat_3.5) |
|
- **Finetuned on data:** |
|
- [ibleducation/ibl-best-practices-instructor-dataset](https://huggingface.co/datasets/ibleducation/ibl-best-practices-instructor-dataset) |
|
- **Model License:** Apache 2.0 |
|
|
|
## How to Use ibl-tutoring-chat-7B Model from Python Code (HuggingFace transformers) ## |
|
|
|
### Install the necessary packages |
|
|
|
Requires: [transformers](https://pypi.org/project/transformers/) 4.35.0 or later, and [accelerate](https://pypi.org/project/accelerate/) 0.23.0 or later. |
|
|
|
```shell |
|
pip install transformers==4.35.0 |
|
pip install accelerate==0.23.0 |
|
``` |
|
### You can then try the following example code |
|
|
|
```python |
|
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> |
|
``` |
