Instructions to use esenergun/gpt_small_enwik8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use esenergun/gpt_small_enwik8 with Transformers:

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

pipe = pipeline("text-generation", model="esenergun/gpt_small_enwik8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("esenergun/gpt_small_enwik8")
model = AutoModelForCausalLM.from_pretrained("esenergun/gpt_small_enwik8")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use esenergun/gpt_small_enwik8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "esenergun/gpt_small_enwik8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "esenergun/gpt_small_enwik8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/esenergun/gpt_small_enwik8

SGLang

How to use esenergun/gpt_small_enwik8 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 "esenergun/gpt_small_enwik8" \
    --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": "esenergun/gpt_small_enwik8",
		"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 "esenergun/gpt_small_enwik8" \
        --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": "esenergun/gpt_small_enwik8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use esenergun/gpt_small_enwik8 with Docker Model Runner:
```
docker model run hf.co/esenergun/gpt_small_enwik8
```

esenergun commited on Mar 21, 2024

Commit

9225e65

verified ·

1 Parent(s): 12e8b46

Training in progress, step 110000

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Mar21_07-39-00_gpu-base-1-59g27/events.out.tfevents.1711006743.gpu-base-1-59g27.54.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab48e26f7a337bc0a595b6cb2e3d7445adec35eb365caa9740d3e0afc43cdb20
 size 435544704

 version https://git-lfs.github.com/spec/v1
+oid sha256:88e5da7dde572b804768d1471258ecc5a95a047f079ef4d4520038169f150d90
 size 435544704

runs/Mar21_07-39-00_gpu-base-1-59g27/events.out.tfevents.1711006743.gpu-base-1-59g27.54.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6e6aef7c3a6109a4fdd9b261d39bab9c2ed6b045f3b39513fa8ac58f5b9da3
-size 9782

 version https://git-lfs.github.com/spec/v1
+oid sha256:72ba34ccf3fc20281de3ef9e93047ee4454e21f359af689bec34d6837a50118f
+size 10273