Instructions to use headmediadesign/gpt2-nathan with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use headmediadesign/gpt2-nathan with Transformers:

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

pipe = pipeline("text-generation", model="headmediadesign/gpt2-nathan")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("headmediadesign/gpt2-nathan")
model = AutoModelForCausalLM.from_pretrained("headmediadesign/gpt2-nathan")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use headmediadesign/gpt2-nathan with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "headmediadesign/gpt2-nathan"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "headmediadesign/gpt2-nathan",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/headmediadesign/gpt2-nathan

SGLang

How to use headmediadesign/gpt2-nathan 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 "headmediadesign/gpt2-nathan" \
    --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": "headmediadesign/gpt2-nathan",
		"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 "headmediadesign/gpt2-nathan" \
        --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": "headmediadesign/gpt2-nathan",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use headmediadesign/gpt2-nathan with Docker Model Runner:
```
docker model run hf.co/headmediadesign/gpt2-nathan
```

headmediadesign commited on Mar 16, 2023

Commit

3085beb

1 Parent(s): 26fad55

Training in progress, step 1000

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Mar16_05-54-42_ba8473751311/events.out.tfevents.1678946097.ba8473751311.6474.11 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:295b3e811fa283fe0fb5cada9c15d79df0e73dc5ac33c4c9342e7456f8a15948
 size 510398013

 version https://git-lfs.github.com/spec/v1
+oid sha256:bfc85557655e036be87a9e28b77aa52d05db63376899f60ae423e1ddd2742782
 size 510398013

runs/Mar16_05-54-42_ba8473751311/events.out.tfevents.1678946097.ba8473751311.6474.11 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a594cf1b202f4fd1400b0fd80b337910cf5f98591c9f155c212b1c1b148843ea
-size 4883

 version https://git-lfs.github.com/spec/v1
+oid sha256:179c444078095bdf0c5258022fb1f5db7137b86e7ab7f6e2e5818614b4de352b
+size 5582