Instructions to use breadlicker45/gpt-something with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use breadlicker45/gpt-something with Transformers:

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

pipe = pipeline("text-generation", model="breadlicker45/gpt-something")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("breadlicker45/gpt-something")
model = AutoModelForCausalLM.from_pretrained("breadlicker45/gpt-something")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use breadlicker45/gpt-something with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "breadlicker45/gpt-something"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "breadlicker45/gpt-something",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/breadlicker45/gpt-something

SGLang

How to use breadlicker45/gpt-something 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 "breadlicker45/gpt-something" \
    --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": "breadlicker45/gpt-something",
		"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 "breadlicker45/gpt-something" \
        --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": "breadlicker45/gpt-something",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use breadlicker45/gpt-something with Docker Model Runner:
```
docker model run hf.co/breadlicker45/gpt-something
```

gpt-something

Commit History

Adding `safetensors` variant of this model

8ad32a0

SFconvertbot commited on Apr 4, 2023

Update README.md

46fe99a

breadlicker45 commited on Dec 23, 2022

Upload tokenizer.json

ff6391b

breadlicker45 commited on Dec 23, 2022

Delete pytorch_model.zip

f50e0d6

breadlicker45 commited on Dec 4, 2022

Upload pytorch_model.bin

20890a9

breadlicker45 commited on Dec 4, 2022

Upload config.json

f074a94

breadlicker45 commited on Dec 4, 2022

Upload pytorch_model.zip

23d3621

breadlicker45 commited on Dec 4, 2022

Upload aitextgen.tokenizer.json

eeb0505

breadlicker45 commited on Dec 4, 2022

initial commit

5d6b94b

matthew mitton commited on Dec 4, 2022

Commit History

Adding `safetensors` variant of this model 8ad32a0

Update README.md 46fe99a

Upload tokenizer.json ff6391b

Delete pytorch_model.zip f50e0d6

Upload pytorch_model.bin 20890a9

Upload config.json f074a94

Upload pytorch_model.zip 23d3621

Upload aitextgen.tokenizer.json eeb0505

initial commit 5d6b94b

Adding `safetensors` variant of this model

8ad32a0

Update README.md

46fe99a

Upload tokenizer.json

ff6391b

Delete pytorch_model.zip

f50e0d6

Upload pytorch_model.bin

20890a9

Upload config.json

f074a94

Upload pytorch_model.zip

23d3621

Upload aitextgen.tokenizer.json

eeb0505

initial commit

5d6b94b