Text Generation
Transformers
Safetensors
English
flygpt
connectome
fruit-fly
drosophila
malecns
recurrent
sparse
tiny-shakespeare
custom_code
Instructions to use QuixiAI/FlyGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use QuixiAI/FlyGPT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="QuixiAI/FlyGPT", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("QuixiAI/FlyGPT", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use QuixiAI/FlyGPT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "QuixiAI/FlyGPT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "QuixiAI/FlyGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/QuixiAI/FlyGPT
- SGLang
How to use QuixiAI/FlyGPT 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 "QuixiAI/FlyGPT" \ --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": "QuixiAI/FlyGPT", "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 "QuixiAI/FlyGPT" \ --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": "QuixiAI/FlyGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use QuixiAI/FlyGPT with Docker Model Runner:
docker model run hf.co/QuixiAI/FlyGPT
Download full-cns/graph_metadata.json from QuixiAI/FlyGPT: direct link, hf CLI and curl.
- Browser
- Download file 1.98 kB
-
https://huggingface.co/QuixiAI/FlyGPT/resolve/main/full-cns/graph_metadata.json
- Command line
-
hf download hf://QuixiAI/FlyGPT/full-cns/graph_metadata.json
-
curl -L -o graph_metadata.json https://huggingface.co/QuixiAI/FlyGPT/resolve/main/full-cns/graph_metadata.json
1.98 kB
| { | |
| "graph_name": "cns_full", | |
| "condition": "real", | |
| "control_seed": 1, | |
| "source": "malecns-v1.0", | |
| "region_filter": "whole_cns", | |
| "min_synapses": 3, | |
| "selector": "directed_core", | |
| "target_neurons": 200000, | |
| "hash": "d53f26f9bf6f7b8c9944e28fdd4721d2c0a237e7534f9160977c70e6c81ac6c2", | |
| "stats": { | |
| "candidate_pool": 164587, | |
| "candidate_edges": 25563096, | |
| "min_synapses": 3, | |
| "target_neurons": 200000, | |
| "edges_after_threshold": 10510984, | |
| "scc_after_threshold": 160514, | |
| "note": "SCC no larger than target; no pruning or trimming applied", | |
| "core_k": 0, | |
| "final_neurons": 160514, | |
| "final_edges": 10402842, | |
| "source": "malecns-v1.0", | |
| "n_neurons": 160514, | |
| "n_edges": 10402842, | |
| "synaptic_contacts": 102352176.0, | |
| "largest_scc_fraction": 1.0, | |
| "reciprocal_pairs": 1006326, | |
| "in_degree": { | |
| "mean": 64.80956178277285, | |
| "min": 1, | |
| "max": 9193 | |
| }, | |
| "out_degree": { | |
| "mean": 64.80956178277285, | |
| "min": 1, | |
| "max": 7749 | |
| }, | |
| "density": 0.00040376518900508274, | |
| "hash": "d53f26f9bf6f7b8c9944e28fdd4721d2c0a237e7534f9160977c70e6c81ac6c2", | |
| "region_breakdown": { | |
| "optic_lobe": 91082, | |
| "central_brain": 36625, | |
| "vnc": 19300, | |
| "other": 13454, | |
| "unannotated": 53 | |
| } | |
| }, | |
| "diagnostics": { | |
| "provenance": { | |
| "control": "real" | |
| }, | |
| "io": { | |
| "n_input": 2048, | |
| "n_output": 4096, | |
| "input_rule": "top_out_degree", | |
| "output_rule": "top_in_degree", | |
| "overlap": 1381 | |
| }, | |
| "diagnostics": { | |
| "n_neurons": 160514, | |
| "n_edges": 10402842, | |
| "largest_scc_fraction": 1.0, | |
| "reciprocal_pairs": 1006326, | |
| "io_reachable_fraction": 1.0, | |
| "io_path_median": 1.0, | |
| "io_path_p90": 1.0, | |
| "io_path_max": 1.0 | |
| }, | |
| "gate": { | |
| "microsteps": 2, | |
| "max_p90_hops": 6, | |
| "min_reachable_fraction": 0.95, | |
| "reachable_ok": true, | |
| "p90_ok": true, | |
| "passed": true | |
| } | |
| } | |
| } |