Instructions to use sillon/DialoGPT-medium-HospitalBot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sillon/DialoGPT-medium-HospitalBot with Transformers:

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

pipe = pipeline("text-generation", model="sillon/DialoGPT-medium-HospitalBot")

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

tokenizer = AutoTokenizer.from_pretrained("sillon/DialoGPT-medium-HospitalBot")
model = AutoModelForCausalLM.from_pretrained("sillon/DialoGPT-medium-HospitalBot", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sillon/DialoGPT-medium-HospitalBot with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/sillon/DialoGPT-medium-HospitalBot

SGLang

How to use sillon/DialoGPT-medium-HospitalBot 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 "sillon/DialoGPT-medium-HospitalBot" \
    --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": "sillon/DialoGPT-medium-HospitalBot",
		"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 "sillon/DialoGPT-medium-HospitalBot" \
        --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": "sillon/DialoGPT-medium-HospitalBot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sillon/DialoGPT-medium-HospitalBot with Docker Model Runner:
```
docker model run hf.co/sillon/DialoGPT-medium-HospitalBot
```

DialoGPT-medium-HospitalBot

Commit History

Jul 14, 2023

12:42
Adding `safetensors` variant of this model⁠

SFconvertbot

a2691eb

May 11, 2023

08:13
Update README.md

sillon

9d732fb
08:12
Create README.md

sillon

0129e23
08:12
Create README.md

sillon

acc173e
08:02
Upload tokenizer

sillon

3a0577a
08:02
Upload model

sillon

7c8f63c
07:51
initial commit

sillon

2bd1969

Commit History

Jul 14, 2023

Adding `safetensors` variant of this model⁠

May 11, 2023

Update README.md

Create README.md

Create README.md

Upload tokenizer

Upload model

initial commit