Text Generation
Transformers
Safetensors
English
qwen3_5_moe
image-text-to-text
agent
deep-research
reasoning
tool-use
long-context
qwen3.5
mixture-of-experts
conversational
Instructions to use cfli/A-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cfli/A-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cfli/A-base") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("cfli/A-base") model = AutoModelForMultimodalLM.from_pretrained("cfli/A-base", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use cfli/A-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "cfli/A-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cfli/A-base", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cfli/A-base
- SGLang
How to use cfli/A-base 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 "cfli/A-base" \ --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": "cfli/A-base", "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 "cfli/A-base" \ --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": "cfli/A-base", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cfli/A-base with Docker Model Runner:
docker model run hf.co/cfli/A-base
| #!/usr/bin/env python3 | |
| """Run one AREX BrowseComp generation through an OpenAI-compatible endpoint.""" | |
| from __future__ import annotations | |
| import argparse | |
| import os | |
| from prompts import build_messages | |
| def parse_args() -> argparse.Namespace: | |
| parser = argparse.ArgumentParser() | |
| parser.add_argument("--question", required=True) | |
| parser.add_argument( | |
| "--base-url", | |
| default=os.environ.get("AREX_BASE_URL", "http://127.0.0.1:8000/v1"), | |
| ) | |
| parser.add_argument( | |
| "--api-key", | |
| default=os.environ.get("AREX_API_KEY", "EMPTY"), | |
| ) | |
| parser.add_argument( | |
| "--model", | |
| default=os.environ.get("AREX_MODEL", "AREX-Base"), | |
| ) | |
| parser.add_argument("--max-tokens", type=int, default=8192) | |
| return parser.parse_args() | |
| def main() -> None: | |
| args = parse_args() | |
| try: | |
| from openai import OpenAI | |
| except ImportError as exc: | |
| raise SystemExit("Install the client first: pip install -U openai") from exc | |
| client = OpenAI( | |
| base_url=args.base_url.rstrip("/") + "/", | |
| api_key=args.api_key, | |
| timeout=600.0, | |
| ) | |
| response = client.chat.completions.create( | |
| model=args.model, | |
| messages=build_messages(args.question), | |
| max_tokens=args.max_tokens, | |
| temperature=1.0, | |
| top_p=0.95, | |
| presence_penalty=1.5, | |
| extra_body={"top_k": 20}, | |
| ) | |
| print(response.choices[0].message.content or "") | |
| if __name__ == "__main__": | |
| main() | |