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

Libraries

How to use Pranavagrl/gpt2-wikitext2 with Transformers:

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Pranavagrl/gpt2-wikitext2 with vLLM:

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

Pranavagrl commited on Jul 28, 2023

Commit

f8d4f03

1 Parent(s): f659f91

Training in progress, step 2000

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Jul28_05-36-52_943cb3168c2b/events.out.tfevents.1690523342.943cb3168c2b.176.0 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18b5025c252edc0feb5319f596b31b358fb406b3044d1830243072ff71f8c22f
 size 497807197

 version https://git-lfs.github.com/spec/v1
+oid sha256:124a11b9fe982c5483958d3fbf62b19e332b513b412cc7d172ea89f60c4993c5
 size 497807197

runs/Jul28_05-36-52_943cb3168c2b/events.out.tfevents.1690523342.943cb3168c2b.176.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e7768be49569d3bd82c948c235d6abe2ce7f34b76c56f39ec08f4c48cbfb59d
-size 5015

 version https://git-lfs.github.com/spec/v1
+oid sha256:0ff5c10dd3d104e1c5750cf07f60312944e5bc8053e09c77cd81e0e467e7ffab
+size 5172