Instructions to use seanmor5/tiny-gpt-neox-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use seanmor5/tiny-gpt-neox-test with Transformers:

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

pipe = pipeline("text-generation", model="seanmor5/tiny-gpt-neox-test")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("seanmor5/tiny-gpt-neox-test")
model = AutoModelForCausalLM.from_pretrained("seanmor5/tiny-gpt-neox-test")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use seanmor5/tiny-gpt-neox-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "seanmor5/tiny-gpt-neox-test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "seanmor5/tiny-gpt-neox-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/seanmor5/tiny-gpt-neox-test

SGLang

How to use seanmor5/tiny-gpt-neox-test 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 "seanmor5/tiny-gpt-neox-test" \
    --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": "seanmor5/tiny-gpt-neox-test",
		"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 "seanmor5/tiny-gpt-neox-test" \
        --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": "seanmor5/tiny-gpt-neox-test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use seanmor5/tiny-gpt-neox-test with Docker Model Runner:
```
docker model run hf.co/seanmor5/tiny-gpt-neox-test
```

tiny-gpt-neox-test

Commit History

Adding `safetensors` variant of this model (#1)

5f58105
verified

seanmor5

SFconvertbot commited on Feb 7, 2024

Upload GPTNeoXForCausalLM

d355802

seanmor5 commited on Apr 21, 2023

Upload model

34babf6

seanmor5 commited on Apr 21, 2023

initial commit

fe2f5af

seanmor5 commited on Apr 21, 2023

Commit History

Adding `safetensors` variant of this model (#1) 5f58105 verified

Upload GPTNeoXForCausalLM d355802

Upload model 34babf6

initial commit fe2f5af

Adding `safetensors` variant of this model (#1)

5f58105
verified

Upload GPTNeoXForCausalLM

d355802

Upload model

34babf6

initial commit

fe2f5af