Instructions to use PDG/gpt2_ft_police_articles with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PDG/gpt2_ft_police_articles with Transformers:

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

pipe = pipeline("text-generation", model="PDG/gpt2_ft_police_articles", device_map="auto")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PDG/gpt2_ft_police_articles")
model = AutoModelForCausalLM.from_pretrained("PDG/gpt2_ft_police_articles", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PDG/gpt2_ft_police_articles with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PDG/gpt2_ft_police_articles"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PDG/gpt2_ft_police_articles",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PDG/gpt2_ft_police_articles

SGLang

How to use PDG/gpt2_ft_police_articles 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 "PDG/gpt2_ft_police_articles" \
    --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": "PDG/gpt2_ft_police_articles",
		"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 "PDG/gpt2_ft_police_articles" \
        --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": "PDG/gpt2_ft_police_articles",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PDG/gpt2_ft_police_articles with Docker Model Runner:
```
docker model run hf.co/PDG/gpt2_ft_police_articles
```

PDG commited on Feb 1, 2023

Commit

4828ece

1 Parent(s): e91decd

Model save

Browse files

Files changed (3) hide show

generation_config.json +6 -0
pytorch_model.bin +1 -1
runs/Feb01_09-25-49_1df9164d7de5/events.out.tfevents.1675244291.1df9164d7de5.440.0 +2 -2

generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.26.0"
+}

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdd9b1337f0ce3e28cce9a4db7a498ac533979de3cce4f6d7c064c0b8b49a024
 size 510398013

 version https://git-lfs.github.com/spec/v1
+oid sha256:c56ee9f4a8801b8a4adc82dc5b5644ed6f1967b8a7c49c1051e5d0be0b75ac46
 size 510398013

runs/Feb01_09-25-49_1df9164d7de5/events.out.tfevents.1675244291.1df9164d7de5.440.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86bfe1034ceb0ad2fe3cd71501511a02340498c9b26ed72758b03f4ef5aad1de
-size 22472

 version https://git-lfs.github.com/spec/v1
+oid sha256:d17098ea9f4fe4c3eaa67f10ae800c26c9eb63c4cc12f5f19e2ad2a70d74e865
+size 22826