Instructions to use projecte-aina/FLOR-6.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use projecte-aina/FLOR-6.3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="projecte-aina/FLOR-6.3B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("projecte-aina/FLOR-6.3B") model = AutoModelForCausalLM.from_pretrained("projecte-aina/FLOR-6.3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use projecte-aina/FLOR-6.3B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "projecte-aina/FLOR-6.3B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "projecte-aina/FLOR-6.3B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/projecte-aina/FLOR-6.3B
- SGLang
How to use projecte-aina/FLOR-6.3B 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 "projecte-aina/FLOR-6.3B" \ --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": "projecte-aina/FLOR-6.3B", "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 "projecte-aina/FLOR-6.3B" \ --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": "projecte-aina/FLOR-6.3B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use projecte-aina/FLOR-6.3B with Docker Model Runner:
docker model run hf.co/projecte-aina/FLOR-6.3B
Template format
Hi!
I have been trying to convert and quantize the model so it can be used in Ollama. One of the steps requieres a TEMPLATE definition, that describes the kind of format used in in the model. I haven't found that info in the model card. I have looked for the documentation of the BLOOM project and the format appears to be:
TEMPLATE "[INST] {{ .Prompt }} [/INST]"
However, when I use that format with the base FLOR-6.3B model, I am getting lots of repetitions in the output, including the [/INST] token. Maybe this is because this format is only used in the Instruct version.
Is there any particular format that needs to be used to produce the outputs of the FLOR-6.3B base model?