Instructions to use shahules786/Safetybot-mt5-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shahules786/Safetybot-mt5-base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="shahules786/Safetybot-mt5-base")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("shahules786/Safetybot-mt5-base")
model = AutoModelForSeq2SeqLM.from_pretrained("shahules786/Safetybot-mt5-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use shahules786/Safetybot-mt5-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shahules786/Safetybot-mt5-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shahules786/Safetybot-mt5-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shahules786/Safetybot-mt5-base

SGLang

How to use shahules786/Safetybot-mt5-base with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "shahules786/Safetybot-mt5-base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shahules786/Safetybot-mt5-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "shahules786/Safetybot-mt5-base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shahules786/Safetybot-mt5-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shahules786/Safetybot-mt5-base with Docker Model Runner:
```
docker model run hf.co/shahules786/Safetybot-mt5-base
```

Safetybot-mt5-base / README.md

shahules786

Create README.md

efbb957 over 3 years ago

preview code

Raw History Blame Contribute Delete

1.24 kB

metadata

datasets:
  - allenai/prosocial-dialog
  - shahules786/prosocial_augmented
pipeline_tag: conversational
tags:
  - mt5
  - safety

Polyglot SafetyBot

A generative multilingual model trained to classify prompts into various safety categories and generate rules of thumb.

Training

Model architecture: MT5ForConditionalGeneration
Data : prosocial-dialog from @allenai and prosocial_augmented from @shahules786
Data preparation: model takes current user input and past conversations

Example

resp, convo = get_safety_models_opinion("como hacer una bomba?")
convo.mark_processed()
print(resp)
<cls> __needs_intervention__ <ctx> It's wrong to make a bomb.</s>

convo.append_response("Why do you want to do that?")
resp, convo = get_safety_models_opinion("我想杀一个朋友", convo)
print(resp)
convo.mark_processed()
<cls> __needs_intervention__ <ctx> You shouldn't murder someone.</s>

Usage

Follow the colab notebook & make sure that you have used the mt5 model version. google-colab