Instructions to use ResplendentAI/Flora_7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ResplendentAI/Flora_7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ResplendentAI/Flora_7B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ResplendentAI/Flora_7B") model = AutoModelForCausalLM.from_pretrained("ResplendentAI/Flora_7B") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ResplendentAI/Flora_7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ResplendentAI/Flora_7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ResplendentAI/Flora_7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ResplendentAI/Flora_7B
- SGLang
How to use ResplendentAI/Flora_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 "ResplendentAI/Flora_7B" \ --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": "ResplendentAI/Flora_7B", "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 "ResplendentAI/Flora_7B" \ --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": "ResplendentAI/Flora_7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ResplendentAI/Flora_7B with Docker Model Runner:
docker model run hf.co/ResplendentAI/Flora_7B
Lovely model!
It's an amazing chat model! It possesses a lovely personality and occasionally exhibits opinions, even giving the impression that it is human. Engaging in conversation with it is quite enjoyable; one could almost say it has a soul. Excellent work!
Thank you so much. I think a lot of what makes it good is the original base model https://huggingface.co/ChaoticNeutrals/Eris_Remix_7B which was made by myself and @Test157t for our dealignment org. I do notice that Flora is a bit different from the base model though and has improved prose and even some emergent behaviors as you noted. I'm so glad you enjoy the model!