Instructions to use monology/largefalcon with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use monology/largefalcon with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="monology/largefalcon")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("monology/largefalcon") model = AutoModelForCausalLM.from_pretrained("monology/largefalcon") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use monology/largefalcon with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "monology/largefalcon" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "monology/largefalcon", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/monology/largefalcon
- SGLang
How to use monology/largefalcon 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 "monology/largefalcon" \ --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": "monology/largefalcon", "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 "monology/largefalcon" \ --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": "monology/largefalcon", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use monology/largefalcon with Docker Model Runner:
docker model run hf.co/monology/largefalcon
largefalcon
This is a frankenmerge of tiiuae/falcon-180B created using mergekit.
Merge Details
The following YAML configuration was used to produce this model:
dtype: float16
merge_method: passthrough
slices:
- sources:
- layer_range: [0, 20]
model: tiiuae/falcon-180B
- sources:
- layer_range: [10, 30]
model: tiiuae/falcon-180B
- sources:
- layer_range: [20, 40]
model: tiiuae/falcon-180B
- sources:
- layer_range: [30, 50]
model: tiiuae/falcon-180B
- sources:
- layer_range: [40, 60]
model: tiiuae/falcon-180B
- sources:
- layer_range: [50, 70]
model: tiiuae/falcon-180B
- sources:
- layer_range: [60, 80]
model: tiiuae/falcon-180B
- Downloads last month
- 81
Model tree for monology/largefalcon
Base model
tiiuae/falcon-180B