Text Generation
Transformers
TensorBoard
Safetensors
biology
genomics
rna
sequence-generation
regression
reinforcement-learning
git-lfs
Instructions to use JoyXiangLab/rnaseek-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JoyXiangLab/rnaseek-full with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="JoyXiangLab/rnaseek-full")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("JoyXiangLab/rnaseek-full", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use JoyXiangLab/rnaseek-full with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "JoyXiangLab/rnaseek-full" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JoyXiangLab/rnaseek-full", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/JoyXiangLab/rnaseek-full
- SGLang
How to use JoyXiangLab/rnaseek-full 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 "JoyXiangLab/rnaseek-full" \ --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": "JoyXiangLab/rnaseek-full", "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 "JoyXiangLab/rnaseek-full" \ --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": "JoyXiangLab/rnaseek-full", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use JoyXiangLab/rnaseek-full with Docker Model Runner:
docker model run hf.co/JoyXiangLab/rnaseek-full
| #!/usr/bin/env python3 | |
| import argparse | |
| import zipfile | |
| from pathlib import Path | |
| SKIP_DIRS = { | |
| ".git", | |
| ".hf-push.git", | |
| ".hf-lfs-cache", | |
| "portable_runtime", | |
| } | |
| def iter_safetensors(root: Path): | |
| for path in root.rglob("*.safetensors"): | |
| rel_parts = path.relative_to(root).parts | |
| if any(part in SKIP_DIRS for part in rel_parts): | |
| continue | |
| yield path | |
| def zip_one(root: Path, path: Path, keep: bool) -> Path: | |
| rel = path.relative_to(root) | |
| out_path = path.with_suffix(path.suffix + ".zip") | |
| tmp_path = path.with_suffix(path.suffix + ".zip.tmp") | |
| if out_path.exists(): | |
| raise FileExistsError(f"Refusing to overwrite existing archive: {out_path}") | |
| with zipfile.ZipFile(tmp_path, "w", compression=zipfile.ZIP_STORED, allowZip64=True) as archive: | |
| archive.write(path, arcname=str(rel)) | |
| tmp_path.replace(out_path) | |
| if not keep: | |
| path.unlink() | |
| return out_path | |
| def main(): | |
| parser = argparse.ArgumentParser( | |
| description="Store every project .safetensors file as .safetensors.zip." | |
| ) | |
| parser.add_argument("--root", type=Path, default=Path.cwd()) | |
| parser.add_argument("--keep", action="store_true", help="Keep original .safetensors files.") | |
| args = parser.parse_args() | |
| root = args.root.resolve() | |
| files = list(iter_safetensors(root)) | |
| print(f"Found {len(files)} .safetensors files under {root}") | |
| for idx, path in enumerate(files, start=1): | |
| rel = path.relative_to(root) | |
| size_gib = path.stat().st_size / (1024 ** 3) | |
| print(f"[{idx}/{len(files)}] zipping {rel} ({size_gib:.2f} GiB)", flush=True) | |
| out_path = zip_one(root, path, keep=args.keep) | |
| print(f" wrote {out_path.relative_to(root)}", flush=True) | |
| if __name__ == "__main__": | |
| main() | |