Instructions to use siddharthbulia/therapy-bot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use siddharthbulia/therapy-bot with Transformers:

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

pipe = pipeline("text-generation", model="siddharthbulia/therapy-bot")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("siddharthbulia/therapy-bot")
model = AutoModelForCausalLM.from_pretrained("siddharthbulia/therapy-bot", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use siddharthbulia/therapy-bot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "siddharthbulia/therapy-bot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "siddharthbulia/therapy-bot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/siddharthbulia/therapy-bot

SGLang

How to use siddharthbulia/therapy-bot 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 "siddharthbulia/therapy-bot" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "siddharthbulia/therapy-bot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "siddharthbulia/therapy-bot" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "siddharthbulia/therapy-bot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use siddharthbulia/therapy-bot with Docker Model Runner:
```
docker model run hf.co/siddharthbulia/therapy-bot
```

siddharthbulia commited on Sep 2, 2023

Commit

ca88707

1 Parent(s): 2d7a8b1

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ tags:
 ## Nintee Therapy Bot
 Built an extremely helpful therapist bot who engages the patient and help the patient open up.
-The Bot is extremely patient, empathetic to the patient, wants best for the patient and give actionable advise to the patient which patient can use to improve his day-to-day life.
 Bot is trained on Data from [Pandora](https://www.kaggle.com/datasets/elvis23/mental-health-conversational-data) dataset.
 In the V2 version of Bot, Nintee Bot will leverage real transcripts from patients and world class therapist with proper consent from patient with complete anonymity.

 ## Nintee Therapy Bot
 Built an extremely helpful therapist bot who engages the patient and help the patient open up.
+The Bot has extremely high patient, knows everything about therapy and mental well-being, empathetic to the patient, wants best for the patient and give actionable advise to the patient which patient can use to improve his day-to-day life.
 Bot is trained on Data from [Pandora](https://www.kaggle.com/datasets/elvis23/mental-health-conversational-data) dataset.
 In the V2 version of Bot, Nintee Bot will leverage real transcripts from patients and world class therapist with proper consent from patient with complete anonymity.