How to use bradduy/banhmi-gemma4-e4b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-4-E4B-it-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "bradduy/banhmi-gemma4-e4b")
How to use bradduy/banhmi-gemma4-e4b with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf bradduy/banhmi-gemma4-e4b:Q3_K_S # Run inference directly in the terminal: llama cli -hf bradduy/banhmi-gemma4-e4b:Q3_K_S
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf bradduy/banhmi-gemma4-e4b:Q3_K_S # Run inference directly in the terminal: llama cli -hf bradduy/banhmi-gemma4-e4b:Q3_K_S
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf bradduy/banhmi-gemma4-e4b:Q3_K_S # Run inference directly in the terminal: ./llama-cli -hf bradduy/banhmi-gemma4-e4b:Q3_K_S
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf bradduy/banhmi-gemma4-e4b:Q3_K_S # Run inference directly in the terminal: ./build/bin/llama-cli -hf bradduy/banhmi-gemma4-e4b:Q3_K_S
docker model run hf.co/bradduy/banhmi-gemma4-e4b:Q3_K_S
How to use bradduy/banhmi-gemma4-e4b with vLLM:
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bradduy/banhmi-gemma4-e4b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bradduy/banhmi-gemma4-e4b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'
How to use bradduy/banhmi-gemma4-e4b with Ollama:
ollama run hf.co/bradduy/banhmi-gemma4-e4b:Q3_K_S
How to use bradduy/banhmi-gemma4-e4b with Docker Model Runner:
How to use bradduy/banhmi-gemma4-e4b with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull bradduy/banhmi-gemma4-e4b:Q3_K_S
lemonade run user.banhmi-gemma4-e4b-Q3_K_S
lemonade list
