Text Generation
Transformers
Safetensors
English
reasoning
mathematics
programming
creative-writing
chain-of-thought
interpretability
fairness
security
deployment
sustainability
monitoring
plugin
Instructions to use BrelloES/brello-thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BrelloES/brello-thinking with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BrelloES/brello-thinking")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BrelloES/brello-thinking", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use BrelloES/brello-thinking with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BrelloES/brello-thinking" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BrelloES/brello-thinking", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BrelloES/brello-thinking
- SGLang
How to use BrelloES/brello-thinking 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 "BrelloES/brello-thinking" \ --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": "BrelloES/brello-thinking", "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 "BrelloES/brello-thinking" \ --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": "BrelloES/brello-thinking", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BrelloES/brello-thinking with Docker Model Runner:
docker model run hf.co/BrelloES/brello-thinking
Commit History
-
Update README.md
Verified signature15131af -
Update README.md
Verified signature56bd7c6 -
Update README.md
Verified signaturebd7c5c0 -
Update README.md
Verified signature30c57a7 -
Update README.md
Verified signature65dab30 -
Delete check_status.py
Verified signature8ee3a07 -
Delete model_card.md
Verified signatureeb48b92 -
Delete verify_upload.py
Verified signature323c97e -
Update README.md
Verified signaturea60e3c1 -
Update README.md
Verified signature9feae5f -
Update README.md
Verified signature69217d9 -
Update README.md
Verified signatureb1c2197 -
Update README.md
Verified signatureb0a3a29 -
Update architecture to EpicBrelloV1ForCausalLM for unique Epic Systems branding
46c2384 -
Fix license to use valid Hugging Face license option
7ee0952 -
Remove files from LFS tracking and re-add as regular text files
a48f8da -
Add status check script
5a88eb9 -
Update all files with proper YAML metadata and fix LFS configuration
87a8832 -
Fix Git LFS configuration - remove .md and .py files from LFS tracking
98c4cd8 -
Add comprehensive model card with detailed specifications, benchmarks, and deployment instructions
11c08ad -
Update YAML metadata format
7b93ebe -
Simplify YAML metadata to basic format
e1ff544 -
Fix YAML metadata to resolve Hugging Face display issues
b0a81e1 -
Add upload summary documentation
0dbea2d -
Update model card with proper YAML metadata
7e99fc3 -
Initial commit: Brello Thinking model by Epic Systems, engineered by Rehan Temkar
974d72d