Text Generation
Transformers
Safetensors
Spanish
mistral
clickbait
noticia
spanish
summary
summarization
conversational
text-generation-inference
Instructions to use Iker/ClickbaitFighter-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Iker/ClickbaitFighter-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Iker/ClickbaitFighter-7B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Iker/ClickbaitFighter-7B") model = AutoModelForCausalLM.from_pretrained("Iker/ClickbaitFighter-7B", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Iker/ClickbaitFighter-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Iker/ClickbaitFighter-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Iker/ClickbaitFighter-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Iker/ClickbaitFighter-7B
- SGLang
How to use Iker/ClickbaitFighter-7B 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 "Iker/ClickbaitFighter-7B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Iker/ClickbaitFighter-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "Iker/ClickbaitFighter-7B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Iker/ClickbaitFighter-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Iker/ClickbaitFighter-7B with Docker Model Runner:
docker model run hf.co/Iker/ClickbaitFighter-7B
Update README.md
Browse files
README.md
CHANGED
|
@@ -257,10 +257,12 @@ print(summary.strip().split("\n")[-1]) # Get only the summary, without the promp
|
|
| 257 |
|
| 258 |
Paper coming soon, for now, you can use this citation:
|
| 259 |
```bittext
|
| 260 |
-
@misc{
|
| 261 |
-
|
| 262 |
-
|
| 263 |
-
|
| 264 |
-
|
|
|
|
|
|
|
| 265 |
}
|
| 266 |
```
|
|
|
|
| 257 |
|
| 258 |
Paper coming soon, for now, you can use this citation:
|
| 259 |
```bittext
|
| 260 |
+
@misc{noticia2024,
|
| 261 |
+
title={NoticIA: A Clickbait Article Summarization Dataset in Spanish},
|
| 262 |
+
author={Iker García-Ferrero and Begoña Altuna},
|
| 263 |
+
year={2024},
|
| 264 |
+
eprint={2404.07611},
|
| 265 |
+
archivePrefix={arXiv},
|
| 266 |
+
primaryClass={cs.CL}
|
| 267 |
}
|
| 268 |
```
|