Instructions to use arthurdubrou/Bird with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use arthurdubrou/Bird with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="arthurdubrou/Bird")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("arthurdubrou/Bird") model = AutoModelForCausalLM.from_pretrained("arthurdubrou/Bird") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use arthurdubrou/Bird with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "arthurdubrou/Bird" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "arthurdubrou/Bird", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/arthurdubrou/Bird
- SGLang
How to use arthurdubrou/Bird 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 "arthurdubrou/Bird" \ --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": "arthurdubrou/Bird", "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 "arthurdubrou/Bird" \ --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": "arthurdubrou/Bird", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use arthurdubrou/Bird with Docker Model Runner:
docker model run hf.co/arthurdubrou/Bird
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="arthurdubrou/Bird")# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("arthurdubrou/Bird")
model = AutoModelForCausalLM.from_pretrained("arthurdubrou/Bird")🐦 Model Card for LLAMA2-Bird-7b
Model Details
Model Description
Bird is a lightweight, fast, and accurate text correction model built upon the Llama architecture. Whether you are working on a document, a blog post, or any form of written communication, Bird will help you produce error-free content by identifying and suggesting corrections for various text errors including but not limited to grammar, punctuation, and spelling.
👩💻[INST] Veuillez corriger ce mail : bonjour monsieur comment allez vous , quelles sont les nouvelles que vous nous apporté ? bien cordailman Arthur [/INST] Bonjour monsieur, comment allez-vous? Quelles sont les nouvelles que vous nous apportez? Bien cordialement, Arthur.
- Developed by: Arthur DUBROU
- Model type: GPT / LLAMA
- Language(s) (NLP): FRENCH
- License: UNDER META LICENSE
- Finetuned from model : LLAMA-7B
- Downloads last month
- -
# Gated model: Login with a HF token with gated access permission hf auth login