Instructions to use kulia-moon/News2GPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kulia-moon/News2GPT with Transformers:

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

pipe = pipeline("text-generation", model="kulia-moon/News2GPT")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kulia-moon/News2GPT")
model = AutoModelForCausalLM.from_pretrained("kulia-moon/News2GPT", device_map="auto")

Transformers.js

How to use kulia-moon/News2GPT with Transformers.js:

// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('text-generation', 'kulia-moon/News2GPT');

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kulia-moon/News2GPT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kulia-moon/News2GPT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kulia-moon/News2GPT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kulia-moon/News2GPT

SGLang

How to use kulia-moon/News2GPT 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 "kulia-moon/News2GPT" \
    --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": "kulia-moon/News2GPT",
		"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 "kulia-moon/News2GPT" \
        --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": "kulia-moon/News2GPT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kulia-moon/News2GPT with Docker Model Runner:
```
docker model run hf.co/kulia-moon/News2GPT
```

kulia-moon commited on Apr 23, 2025

Commit

a91da4a

verified ·

1 Parent(s): 21d7b4c

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -6

README.md CHANGED Viewed

@@ -1,9 +1,17 @@
 ---
-library_name: transformers.js
 base_model:
-- kulia-moon/News2GPT
 ---
-# News2GPT (ONNX)
-This is an ONNX version of [kulia-moon/News2GPT](https://huggingface.co/kulia-moon/News2GPT). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).

 ---
+license: mit
+datasets:
+- abisee/cnn_dailymail
+- SetFit/ag_news
+- Yelp/yelp_review_full
+- rajpurkar/squad
+language:
+- en
 base_model:
+- distilbert/distilgpt2
+library_name: transformers
+tags:
+- news
+- transformers.js
 ---
+# News2GPT (81.9M param with ONNX)