How to use hiteshluke/arbiter-4b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-3-4b-it-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "hiteshluke/arbiter-4b")
How to use hiteshluke/arbiter-4b with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf hiteshluke/arbiter-4b:Q4_K_M # Run inference directly in the terminal: llama cli -hf hiteshluke/arbiter-4b:Q4_K_M
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf hiteshluke/arbiter-4b:Q4_K_M # Run inference directly in the terminal: llama cli -hf hiteshluke/arbiter-4b:Q4_K_M
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf hiteshluke/arbiter-4b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf hiteshluke/arbiter-4b:Q4_K_M
docker model run hf.co/hiteshluke/arbiter-4b:Q4_K_M
How to use hiteshluke/arbiter-4b with Ollama:
ollama run hf.co/hiteshluke/arbiter-4b:Q4_K_M
How to use hiteshluke/arbiter-4b with Docker Model Runner:
How to use hiteshluke/arbiter-4b with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull hiteshluke/arbiter-4b:Q4_K_M
lemonade run user.arbiter-4b-Q4_K_M
lemonade list
