Instructions to use Srish117/gpt2-wikitext2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Srish117/gpt2-wikitext2 with Transformers:

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

pipe = pipeline("text-generation", model="Srish117/gpt2-wikitext2")

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

tokenizer = AutoTokenizer.from_pretrained("Srish117/gpt2-wikitext2")
model = AutoModelForCausalLM.from_pretrained("Srish117/gpt2-wikitext2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Srish117/gpt2-wikitext2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Srish117/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": "Srish117/gpt2-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Srish117/gpt2-wikitext2

SGLang

How to use Srish117/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 "Srish117/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": "Srish117/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 "Srish117/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": "Srish117/gpt2-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Srish117/gpt2-wikitext2 with Docker Model Runner:
```
docker model run hf.co/Srish117/gpt2-wikitext2
```

Srish117 commited on Oct 10, 2023

Commit

c5dc82d

1 Parent(s): c822121

Training in progress, step 6500

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Oct10_09-06-29_b968ac93101e/events.out.tfevents.1696928807.b968ac93101e.3986.0 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f273c2bfa8efcfb42db55a7e4b185b4c58ad1232253149bbaaaa8d53746ab918
 size 510398013

 version https://git-lfs.github.com/spec/v1
+oid sha256:88fc5d8cf1ec04748c7b9c565c037c5553af81c08452f392b714b03c8e9897a4
 size 510398013

runs/Oct10_09-06-29_b968ac93101e/events.out.tfevents.1696928807.b968ac93101e.3986.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f58721affb3b32e93104703ed67f0ac8c61723537ef137fd3b4f0a7680cdcefb
-size 6646

 version https://git-lfs.github.com/spec/v1
+oid sha256:043aeb525b6118d5c4ebcc66975b2c905b8c7829665b839c07a5df9ba00e57ad
+size 6803