Instructions to use brunosan/GPT2-impactscience with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use brunosan/GPT2-impactscience with Transformers:

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

pipe = pipeline("text-generation", model="brunosan/GPT2-impactscience")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("brunosan/GPT2-impactscience")
model = AutoModelForCausalLM.from_pretrained("brunosan/GPT2-impactscience")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use brunosan/GPT2-impactscience with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "brunosan/GPT2-impactscience"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "brunosan/GPT2-impactscience",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/brunosan/GPT2-impactscience

SGLang

How to use brunosan/GPT2-impactscience 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 "brunosan/GPT2-impactscience" \
    --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": "brunosan/GPT2-impactscience",
		"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 "brunosan/GPT2-impactscience" \
        --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": "brunosan/GPT2-impactscience",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use brunosan/GPT2-impactscience with Docker Model Runner:
```
docker model run hf.co/brunosan/GPT2-impactscience
```

GPT2-impactscience

Commit History

Upload gradio_interface.py

8a00478

brunosan commited on Mar 1, 2023

Upload finetune.ipynb

3381014

brunosan commited on Feb 28, 2023

Upload tokenizer

c3ab4bb

brunosan commited on Feb 28, 2023

Upload model

89baaf1

brunosan commited on Feb 28, 2023

Upload tokenizer

03e4e53

brunosan commited on Feb 28, 2023

Upload model

f5848b7

brunosan commited on Feb 28, 2023

Upload 2 files

bf45cf1

brunosan commited on Feb 28, 2023

Upload tokenizer

3316819

brunosan commited on Feb 28, 2023

Upload model

1a79529

brunosan commited on Feb 28, 2023

Upload tokenizer

c26bfd4

brunosan commited on Feb 28, 2023

Upload model

30d984f

brunosan commited on Feb 28, 2023

Upload tokenizer

a8ae124

brunosan commited on Feb 28, 2023

Upload model

915d446

brunosan commited on Feb 28, 2023

Update README.md

eac0a5f

brunosan commited on Feb 28, 2023

Upload tokenizer

b9c8573

brunosan commited on Feb 28, 2023

Upload model

76dc03d

brunosan commited on Feb 28, 2023

Update README.md

1fc38bd

brunosan commited on Feb 28, 2023

Upload model

c37c57a

brunosan commited on Feb 28, 2023

initial commit

3790fc8

Bruno Sánchez-Andrade Nuño commited on Feb 28, 2023

Commit History

Upload gradio_interface.py 8a00478

Upload finetune.ipynb 3381014

Upload tokenizer c3ab4bb

Upload model 89baaf1

Upload tokenizer 03e4e53

Upload model f5848b7

Upload 2 files bf45cf1

Upload tokenizer 3316819

Upload model 1a79529

Upload tokenizer c26bfd4

Upload model 30d984f

Upload tokenizer a8ae124

Upload model 915d446

Update README.md eac0a5f

Upload tokenizer b9c8573

Upload model 76dc03d

Update README.md 1fc38bd

Upload model c37c57a

initial commit 3790fc8

Upload gradio_interface.py

8a00478

Upload finetune.ipynb

3381014

Upload tokenizer

c3ab4bb

Upload model

89baaf1

Upload tokenizer

03e4e53

Upload model

f5848b7

Upload 2 files

bf45cf1

Upload tokenizer

3316819

Upload model

1a79529

Upload tokenizer

c26bfd4

Upload model

30d984f

Upload tokenizer

a8ae124

Upload model

915d446

Update README.md

eac0a5f

Upload tokenizer

b9c8573

Upload model

76dc03d

Update README.md

1fc38bd

Upload model

c37c57a

initial commit

3790fc8