Instructions to use sahajai/clef-finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sahajai/clef-finetune with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="sahajai/clef-finetune")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("sahajai/clef-finetune", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use sahajai/clef-finetune with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sahajai/clef-finetune" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sahajai/clef-finetune", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/sahajai/clef-finetune
- SGLang
How to use sahajai/clef-finetune 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 "sahajai/clef-finetune" \ --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": "sahajai/clef-finetune", "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 "sahajai/clef-finetune" \ --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": "sahajai/clef-finetune", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use sahajai/clef-finetune with Docker Model Runner:
docker model run hf.co/sahajai/clef-finetune
sahajai/clef-finetune
A fine-tune of Cloudflare/clef, the 27B multimodal decision model, by Sahaj.
Status: work in progress. This repository is a placeholder for an upcoming fine-tune. No trained weights have been uploaded yet.
Base model
- Base: Cloudflare/clef, which is built on Qwen/Qwen3.8-27B
- License: Apache-2.0, inherited from the base model
Usage
When weights are published, usage will follow the base model's joint_schema_model interface. See the Cloudflare/clef model card.