Instructions to use tiiuae/falcon-mamba-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tiiuae/falcon-mamba-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="tiiuae/falcon-mamba-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-mamba-7b") model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-mamba-7b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use tiiuae/falcon-mamba-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tiiuae/falcon-mamba-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tiiuae/falcon-mamba-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/tiiuae/falcon-mamba-7b
- SGLang
How to use tiiuae/falcon-mamba-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 "tiiuae/falcon-mamba-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": "tiiuae/falcon-mamba-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 "tiiuae/falcon-mamba-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": "tiiuae/falcon-mamba-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use tiiuae/falcon-mamba-7b with Docker Model Runner:
docker model run hf.co/tiiuae/falcon-mamba-7b
Training Datasets
#9
by zoher15 - opened
Hi,
Was the model trained on any training data from StrategyQA? I was testing its zeroshot performance and it is very high on that specific dataset.
Best,
Zoher
Hi there!
I can confirm that we didn't train the model explicitly on the training data from StrategyQA. However, the recent web data has higher possibility to be contaminated, as discussed here.
Thanks,
Jingwei