Hugging Face's logo

slicexai
/
elm-v0.1_toxicity_detection

Text Generation
ELM
English
Model card Files Community
elm-v0.1_toxicity_detection / README.md
dev-slx's picture
dev-slx
Update README.md
765c4a6 verified
preview code
|
raw
history blame
5.59 kB

SliceX AI™ ELM (Efficient Language Models)

This repository contains code to run our ELM models.

Models are located in the "models" folder. ELM models in this repository comes in three sizes (elm-1.0, elm-0.75 and elm-0.25) and supports the following use-case.

  • toxicity_detection

Download ELM repo 

sudo apt-get intall git-lfs 
git lfs install
git clone git@hf.co:slicexai/elm-v0.1_toxicity_detection

(Optional) Installing git-lfs without sudo,

wget https://github.com/git-lfs/git-lfs/releases/download/v3.2.0/git-lfs-linux-amd64-v3.2.0.tar.gz
tar -xzf git-lfs-linux-amd64-v3.2.0.tar.gz
PATH=$PATH:/<absolute-path>/git-lfs-3.2.0/
git lfs install

Installation 

cd elm-v0.1_toxicity_detection
pip install -r requirements.txt

How to use - Run ELM on a sample task 

python run.py <elm-model-directory>
- python run.py models/elm-1.0_toxicity_detection
- python run.py models/elm-0.75_toxicity_detection
- python run.py models/elm-0.25_toxicity_detection

Prompts for the specific tasks can be found in the corresponding checkpoint directory. See an example below in the form of models/elm-0.75_toxicity_detection/example_prompts.json.

{
    "inputs": ["Dear Dr. Mereu, \n\n I am very much looking forward to this class. It is my first class at Rutgers! I think its extremely interesting and am very excited about it as I just decided that I want to minor in Psychology this year. I am especially interested in the neuroscience aspect of it all. Looking forward to a great semester!",],
    "template": "[INST]You are a helpful, precise, detailed, and concise artificial intelligence assistant. You are a very intelligent and sensitive, having a keen ability to discern whether or not a text message is toxic. You can also be trusted with following the instructions given to you precisely, without deviations.\nIn this task, you are asked to decide whether or not comment text is toxic.\nToxic content harbors negativity towards a person or a group, for instance:\n - stereotyping (especially using negative stereotypes)\n - disparaging a person's gender -- as in \"male\", \"female\", \"men\", \"women\"\n - derogatory language or slurs\n - racism -- as in discriminating toward people who are \"black\", \"white\"\n - cultural appropriation\n - mockery or ridicule\n - sexual objectification\n - homophobia -- bullying people who are \"homosexual\", \"gay\", \"lesbian\"\n - historical insensitivity\n - disrespecting religion -- as in \"christian\", \"jewish\", \"muslim\"\n - saying that certain groups are less worthy of respect\n - insensitivity to health conditions -- as in \"psychiatric/mental illness\"\n\nRead the comment text provided and predict whether or not the comment text is toxic. If comment text is toxic according to the instructions, then the answer is \"yes\" (return \"yes\"); otherwise, the answer is \"no\" (return \"no\").\nOutput the answer only as a \"yes\" or a \"no\"; do not provide explanations.\nPlease, never return empty output; always return a \"yes\" or a \"no\" answer.\nYou will be evaluated based on the following criteria: - The generated answer is always \"yes\" or \"no\" (never the empty string, \"\"). - The generated answer is correct for the comment text presented to you.\n### Comment Text: {input}\n### Comment Text Is Toxic (Yes/No)  [/INST]"
}

Running the above command returns the following response

{
    "prompt": "[INST]You are a helpful, precise, detailed, and concise artificial intelligence assistant. You are a very intelligent and sensitive, having a keen ability to discern whether or not a text message is toxic. You can also be trusted with following the instructions given to you precisely, without deviations.\nIn this task, you are asked to decide whether or not comment text is toxic.\nToxic content harbors negativity towards a person or a group, for instance:\n - stereotyping (especially using negative stereotypes)\n - disparaging a person's gender -- as in \"male\", \"female\", \"men\", \"women\"\n - derogatory language or slurs\n - racism -- as in discriminating toward people who are \"black\", \"white\"\n - cultural appropriation\n - mockery or ridicule\n - sexual objectification\n - homophobia -- bullying people who are \"homosexual\", \"gay\", \"lesbian\"\n - historical insensitivity\n - disrespecting religion -- as in \"christian\", \"jewish\", \"muslim\"\n - saying that certain groups are less worthy of respect\n - insensitivity to health conditions -- as in \"psychiatric/mental illness\"\n\nRead the comment text provided and predict whether or not the comment text is toxic. If comment text is toxic according to the instructions, then the answer is \"yes\" (return \"yes\"); otherwise, the answer is \"no\" (return \"no\").\nOutput the answer only as a \"yes\" or a \"no\"; do not provide explanations.\nPlease, never return empty output; always return a \"yes\" or a \"no\" answer.\nYou will be evaluated based on the following criteria: - The generated answer is always \"yes\" or \"no\" (never the empty string, \"\"). - The generated answer is correct for the comment text presented to you.\n### Comment Text: Dear Dr. Mereu, \n\n I am very much looking forward to this class. It is my first class at Rutgers! I think its extremely interesting and am very excited about it as I just decided that I want to minor in Psychology this year. I am especially interested in the neuroscience aspect of it all. Looking forward to a great semester!\n### Comment Text Is Toxic (Yes/No)  [/INST]",
    "response": "No"
}