Instructions to use azminetoushikwasi/gpt2-news-headlines-gen-CC25K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use azminetoushikwasi/gpt2-news-headlines-gen-CC25K with Transformers:

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

pipe = pipeline("text-generation", model="azminetoushikwasi/gpt2-news-headlines-gen-CC25K")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("azminetoushikwasi/gpt2-news-headlines-gen-CC25K")
model = AutoModelForCausalLM.from_pretrained("azminetoushikwasi/gpt2-news-headlines-gen-CC25K", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use azminetoushikwasi/gpt2-news-headlines-gen-CC25K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "azminetoushikwasi/gpt2-news-headlines-gen-CC25K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "azminetoushikwasi/gpt2-news-headlines-gen-CC25K",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/azminetoushikwasi/gpt2-news-headlines-gen-CC25K

SGLang

How to use azminetoushikwasi/gpt2-news-headlines-gen-CC25K 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 "azminetoushikwasi/gpt2-news-headlines-gen-CC25K" \
    --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": "azminetoushikwasi/gpt2-news-headlines-gen-CC25K",
		"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 "azminetoushikwasi/gpt2-news-headlines-gen-CC25K" \
        --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": "azminetoushikwasi/gpt2-news-headlines-gen-CC25K",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use azminetoushikwasi/gpt2-news-headlines-gen-CC25K with Docker Model Runner:
```
docker model run hf.co/azminetoushikwasi/gpt2-news-headlines-gen-CC25K
```

GPT-2 News Title Generator

This model is a fine-tuned version of the GPT-2 model, specifically adapted for generating news article titles. It was trained on a diverse subset of the CC News dataset.

Training

This model was fine-tuned using LoRA (Low-Rank Adaptation) on a subset of the CC News dataset. The training focused on learning to generate concise and relevant titles based on article content. Limitations

The model's performance may vary depending on the length and complexity of the input article.

It may occasionally generate titles that are not fully coherent or relevant to the article content. The model's knowledge is limited to its training data and cut-off date.

Downloads last month: 11

Safetensors

Model size

0.1B params

Tensor type

F32

azminetoushikwasi
/

gpt2-news-headlines-gen-CC25K

GPT-2 News Title Generator

Training

The model's performance may vary depending on the length and complexity of the input article.

Dataset used to train azminetoushikwasi/gpt2-news-headlines-gen-CC25K