Text Generation
Transformers
Spanish
English
customer-support
question-answering
Dialogue
Chatbot
text2text-generation
Instructions to use Ari-008/CustomerSupportAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ari-008/CustomerSupportAI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ari-008/CustomerSupportAI")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Ari-008/CustomerSupportAI", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ari-008/CustomerSupportAI with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ari-008/CustomerSupportAI" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ari-008/CustomerSupportAI", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Ari-008/CustomerSupportAI
- SGLang
How to use Ari-008/CustomerSupportAI 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 "Ari-008/CustomerSupportAI" \ --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": "Ari-008/CustomerSupportAI", "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 "Ari-008/CustomerSupportAI" \ --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": "Ari-008/CustomerSupportAI", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Ari-008/CustomerSupportAI with Docker Model Runner:
docker model run hf.co/Ari-008/CustomerSupportAI
| license: apache-2.0 | |
| datasets: | |
| - bitext/Bitext-customer-support-llm-chatbot-training-dataset | |
| language: | |
| - es | |
| - en | |
| metrics: | |
| - accuracy | |
| - perplexity | |
| - f1 | |
| - bleu | |
| base_model: | |
| - google-bert/bert-base-multilingual-cased | |
| - nomic-ai/gpt4all-j | |
| - google/flan-t5-large | |
| - stabilityai/stable-diffusion-3-medium | |
| new_version: praneethposina/customer_support_bot | |
| pipeline_tag: text2text-generation | |
| library_name: transformers | |
| tags: | |
| - customer-support | |
| - question-answering | |
| - Dialogue | |
| - Chatbot | |