Instructions to use rahulshah9713/gpt2-wikitext2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rahulshah9713/gpt2-wikitext2 with Transformers:

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

pipe = pipeline("text-generation", model="rahulshah9713/gpt2-wikitext2")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rahulshah9713/gpt2-wikitext2")
model = AutoModelForCausalLM.from_pretrained("rahulshah9713/gpt2-wikitext2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rahulshah9713/gpt2-wikitext2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rahulshah9713/gpt2-wikitext2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rahulshah9713/gpt2-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rahulshah9713/gpt2-wikitext2

SGLang

How to use rahulshah9713/gpt2-wikitext2 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 "rahulshah9713/gpt2-wikitext2" \
    --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": "rahulshah9713/gpt2-wikitext2",
		"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 "rahulshah9713/gpt2-wikitext2" \
        --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": "rahulshah9713/gpt2-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rahulshah9713/gpt2-wikitext2 with Docker Model Runner:
```
docker model run hf.co/rahulshah9713/gpt2-wikitext2
```

rahulshah9713 commited on Feb 14, 2024

Commit

10180cd

verified ·

1 Parent(s): fb4ad11

Training in progress, step 6000

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Feb14_06-37-36_fd77b2d668bb/events.out.tfevents.1707892664.fd77b2d668bb.434.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64db6fdbc602d7abfeeb702df8db8d6d229bc851274ffa98304cc8f63aa0adb0
 size 497774208

 version https://git-lfs.github.com/spec/v1
+oid sha256:c187983acf7525502cec7bf43474c19b306e67ee043e2b6533c02c77f56e9ce7
 size 497774208

runs/Feb14_06-37-36_fd77b2d668bb/events.out.tfevents.1707892664.fd77b2d668bb.434.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ad85c70aab8836c3d56bb7365bed6165e005ced47c6849237d63bab4489058a
-size 6536

 version https://git-lfs.github.com/spec/v1
+oid sha256:1b0d66d698a94bb484fcc05c8b0a3f445dee80dd71ce74411379f6dce55210b4
+size 7007