Instructions to use Pclanglais/Brahe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Pclanglais/Brahe with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Pclanglais/Brahe")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Pclanglais/Brahe") model = AutoModelForCausalLM.from_pretrained("Pclanglais/Brahe") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Pclanglais/Brahe with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Pclanglais/Brahe" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Pclanglais/Brahe", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Pclanglais/Brahe
- SGLang
How to use Pclanglais/Brahe 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 "Pclanglais/Brahe" \ --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": "Pclanglais/Brahe", "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 "Pclanglais/Brahe" \ --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": "Pclanglais/Brahe", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Pclanglais/Brahe with Docker Model Runner:
docker model run hf.co/Pclanglais/Brahe
Create different modes for in-depth annotation
#2
by Pclanglais - opened
The quality (and verifiability) of annotation can be significantly enhanced through reasoning, by generating first a detailed analysis of the text. Due to the context window and performance, this is obviously not doable for all annotations.
I am currently developing a specific variant of Brahe for measuring the passing of time in three steps:
- Identification of explicit time mentions.
- Deductions based on what is narrated in the text (dialogs, actions, etc.)
- Final estimate.
Additional modes could include further important narrative dimensions (maybe building on the narratologic framework of Gérard Genette in Figures III):
- Analysis of narrative voices.
- Mapping of fictional space and geographies.
- Identification of characters and summary of available information (biographical information, psychology, etc.)