Text Generation
Transformers
Safetensors
PEFT
English
reasoning
evidence-grounding
grounded-qa
attribution
fever
hotpotqa
lora
distillation
research
conversational
Instructions to use darcar0/quotebound-27b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use darcar0/quotebound-27b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="darcar0/quotebound-27b") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("darcar0/quotebound-27b", dtype="auto") - PEFT
How to use darcar0/quotebound-27b with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use darcar0/quotebound-27b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "darcar0/quotebound-27b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "darcar0/quotebound-27b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/darcar0/quotebound-27b
- SGLang
How to use darcar0/quotebound-27b 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 "darcar0/quotebound-27b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "darcar0/quotebound-27b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "darcar0/quotebound-27b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "darcar0/quotebound-27b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use darcar0/quotebound-27b with Docker Model Runner:
docker model run hf.co/darcar0/quotebound-27b
| <svg xmlns="http://www.w3.org/2000/svg" width="1160" height="612" viewBox="0 0 1160 612" fill="none"> | |
| <rect width="1160" height="612" rx="28" fill="#fffaf2"/> | |
| <rect x="1" y="1" width="1158" height="610" rx="27" stroke="rgba(29,26,24,0.10)"/> | |
| <text x="64" y="52" font-family="Space Grotesk, sans-serif" font-size="28" font-weight="700" fill="#1d1a18">Benchmark progression on frozen probe_v0</text> | |
| <text x="64" y="78" font-family="IBM Plex Mono, monospace" font-size="12" letter-spacing="1.5" fill="#685e56">MAIN BENCHMARK-FACING STACKS</text> | |
| <g transform="translate(720,48)"> | |
| <rect x="0" y="0" width="14" height="14" rx="7" fill="#1d1a18"/> | |
| <text x="22" y="11" font-size="12" fill="#685e56">task</text> | |
| <rect x="88" y="0" width="14" height="14" rx="7" fill="#ef7c30"/> | |
| <text x="110" y="11" font-size="12" fill="#685e56">strict</text> | |
| <rect x="182" y="0" width="14" height="14" rx="7" fill="#3b7f6a"/> | |
| <text x="204" y="11" font-size="12" fill="#685e56">evidence F1</text> | |
| <rect x="306" y="0" width="14" height="14" rx="7" fill="#7a5cff"/> | |
| <text x="328" y="11" font-size="12" fill="#685e56">quote F1</text> | |
| </g> | |
| <g transform="translate(64,98)"> | |
| <rect x="0" y="0" width="1032" height="88" rx="22" fill="rgba(255,255,255,0.72)" stroke="rgba(29,26,24,0.08)"/> | |
| <text x="20" y="30" font-family="Space Grotesk, sans-serif" font-size="18" font-weight="600" fill="#1d1a18">Old v2 baseline</text> | |
| <g transform="translate(328,16)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="355" height="12" rx="6" fill="#1d1a18" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">task 0.9545</text> | |
| </g> | |
| <g transform="translate(328,34)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="67" height="12" rx="6" fill="#ef7c30" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">strict 0.1818</text> | |
| </g> | |
| <g transform="translate(328,52)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="325" height="12" rx="6" fill="#3b7f6a" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">evidence 0.8758</text> | |
| </g> | |
| <g transform="translate(328,70)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="92" height="12" rx="6" fill="#7a5cff" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">quote 0.2494</text> | |
| </g> | |
| </g> | |
| <g transform="translate(64,206)"> | |
| <rect x="0" y="0" width="1032" height="88" rx="22" fill="rgba(255,255,255,0.72)" stroke="rgba(29,26,24,0.08)"/> | |
| <text x="20" y="30" font-family="Space Grotesk, sans-serif" font-size="18" font-weight="600" fill="#1d1a18">Bridge checkpoint-2</text> | |
| <g transform="translate(328,16)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="#1d1a18" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">task 1.0000</text> | |
| </g> | |
| <g transform="translate(328,34)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="101" height="12" rx="6" fill="#ef7c30" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">strict 0.2727</text> | |
| </g> | |
| <g transform="translate(328,52)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="328" height="12" rx="6" fill="#3b7f6a" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">evidence 0.8844</text> | |
| </g> | |
| <g transform="translate(328,70)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="164" height="12" rx="6" fill="#7a5cff" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">quote 0.4409</text> | |
| </g> | |
| </g> | |
| <g transform="translate(64,314)"> | |
| <rect x="0" y="0" width="1032" height="88" rx="22" fill="rgba(255,255,255,0.72)" stroke="rgba(29,26,24,0.08)"/> | |
| <text x="20" y="30" font-family="Space Grotesk, sans-serif" font-size="18" font-weight="600" fill="#1d1a18">Bridge + deterministic_v2</text> | |
| <g transform="translate(328,16)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="#1d1a18" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">task 1.0000</text> | |
| </g> | |
| <g transform="translate(328,34)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="152" height="12" rx="6" fill="#ef7c30" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">strict 0.4091</text> | |
| </g> | |
| <g transform="translate(328,52)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="328" height="12" rx="6" fill="#3b7f6a" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">evidence 0.8844</text> | |
| </g> | |
| <g transform="translate(328,70)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="214" height="12" rx="6" fill="#7a5cff" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">quote 0.5773</text> | |
| </g> | |
| </g> | |
| <g transform="translate(64,422)"> | |
| <rect x="0" y="0" width="1032" height="88" rx="22" fill="#fff3eb" stroke="rgba(29,26,24,0.08)"/> | |
| <text x="20" y="30" font-family="Space Grotesk, sans-serif" font-size="18" font-weight="600" fill="#1d1a18">Bridge + deterministic_v3</text> | |
| <g transform="translate(328,16)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="#1d1a18" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">task 1.0000</text> | |
| </g> | |
| <g transform="translate(328,34)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="#ef7c30" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">strict 1.0000</text> | |
| </g> | |
| <g transform="translate(328,52)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="#3b7f6a" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">evidence 1.0000</text> | |
| </g> | |
| <g transform="translate(328,70)"> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="rgba(29,26,24,0.08)" /> | |
| <rect x="0" y="0" width="372" height="12" rx="6" fill="#7a5cff" /> | |
| <text x="384" y="10" font-size="12" fill="#685e56">quote 1.0000</text> | |
| </g> | |
| </g> | |
| </svg> | |