How to use shumi2011/gemma-3-4B-it-thinking-function_calling-V0 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-4b-it") model = PeftModel.from_pretrained(base_model, "shumi2011/gemma-3-4B-it-thinking-function_calling-V0")
How to use shumi2011/gemma-3-4B-it-thinking-function_calling-V0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="shumi2011/gemma-3-4B-it-thinking-function_calling-V0") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("shumi2011/gemma-3-4B-it-thinking-function_calling-V0", dtype="auto")
How to use shumi2011/gemma-3-4B-it-thinking-function_calling-V0 with vLLM:
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "shumi2011/gemma-3-4B-it-thinking-function_calling-V0" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "shumi2011/gemma-3-4B-it-thinking-function_calling-V0", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'
docker model run hf.co/shumi2011/gemma-3-4B-it-thinking-function_calling-V0
How to use shumi2011/gemma-3-4B-it-thinking-function_calling-V0 with SGLang:
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "shumi2011/gemma-3-4B-it-thinking-function_calling-V0" \ --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": "shumi2011/gemma-3-4B-it-thinking-function_calling-V0", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'
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 "shumi2011/gemma-3-4B-it-thinking-function_calling-V0" \ --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": "shumi2011/gemma-3-4B-it-thinking-function_calling-V0", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'
How to use shumi2011/gemma-3-4B-it-thinking-function_calling-V0 with Docker Model Runner:
