Instructions to use Santosh-Gupta/EncephalitisGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Santosh-Gupta/EncephalitisGPT with Transformers:

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

pipe = pipeline("text-generation", model="Santosh-Gupta/EncephalitisGPT")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Santosh-Gupta/EncephalitisGPT")
model = AutoModelForCausalLM.from_pretrained("Santosh-Gupta/EncephalitisGPT", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Santosh-Gupta/EncephalitisGPT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Santosh-Gupta/EncephalitisGPT

SGLang

How to use Santosh-Gupta/EncephalitisGPT 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 "Santosh-Gupta/EncephalitisGPT" \
    --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": "Santosh-Gupta/EncephalitisGPT",
		"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 "Santosh-Gupta/EncephalitisGPT" \
        --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": "Santosh-Gupta/EncephalitisGPT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Santosh-Gupta/EncephalitisGPT with Docker Model Runner:
```
docker model run hf.co/Santosh-Gupta/EncephalitisGPT
```

EncephalitisGPT / README.md

Santosh-Gupta

Update README.md

888f89d over 2 years ago

preview code

Raw

History Blame Contribute Delete

667 Bytes

metadata

license: mit

The training of model used Microsoft's bioGPT as a base model, and then finetuned in a dataset of over 370k encephalitis question and answers

https://huggingface.co/datasets/Santosh-Gupta/EncephalitisQuestionAnswering

To use

from transformers import pipeline, AutoTokenizer, AutoModel

model = AutoModel.from_pretrained('Santosh-Gupta/EncephalitisGPT')
tokenizer = AutoTokenizer.from_pretrained('Santosh-Gupta/EncephalitisGPT')

generator = pipeline('text-generation', model=model, tokenizer=tokenizer, device=0)
generator("What are causes of autoimmune encephalitis", max_length=1000, num_return_sequences=1, do_sample=True)