Text Generation
PEFT
Safetensors
GGUF
gemma4
unsloth
lora
qlora
fine-tuning
hackathon
gemma-4-good-hackathon
kaggle
translation
speech-recognition
accessibility
on-device
conversational
Instructions to use bradduy/banhmi-gemma4-e4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
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") - llama-cpp-python
How to use bradduy/banhmi-gemma4-e4b with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="bradduy/banhmi-gemma4-e4b", filename="banhmi-gemma4.Q3_K_S.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use bradduy/banhmi-gemma4-e4b with llama.cpp:
Install from brew
brew install llama.cpp # 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
Install from WinGet (Windows)
winget install llama.cpp # 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
Use pre-built binary
# 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
Build from source code
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
Use Docker
docker model run hf.co/bradduy/banhmi-gemma4-e4b:Q3_K_S
- LM Studio
- Jan
- vLLM
How to use bradduy/banhmi-gemma4-e4b with vLLM:
Install from pip and serve model
# 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?" } ] }'Use Docker
docker model run hf.co/bradduy/banhmi-gemma4-e4b:Q3_K_S
- Ollama
How to use bradduy/banhmi-gemma4-e4b with Ollama:
ollama run hf.co/bradduy/banhmi-gemma4-e4b:Q3_K_S
- Unsloth Studio new
How to use bradduy/banhmi-gemma4-e4b with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for bradduy/banhmi-gemma4-e4b to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for bradduy/banhmi-gemma4-e4b to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for bradduy/banhmi-gemma4-e4b to start chatting
- Docker Model Runner
How to use bradduy/banhmi-gemma4-e4b with Docker Model Runner:
docker model run hf.co/bradduy/banhmi-gemma4-e4b:Q3_K_S
- Lemonade
How to use bradduy/banhmi-gemma4-e4b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull bradduy/banhmi-gemma4-e4b:Q3_K_S
Run and chat with the model
lemonade run user.banhmi-gemma4-e4b-Q3_K_S
List all available models
lemonade list
| { | |
| "audio_token": "<|audio|>", | |
| "backend": "tokenizers", | |
| "boa_token": "<|audio>", | |
| "boi_token": "<|image>", | |
| "bos_token": "<bos>", | |
| "eoa_token": "<audio|>", | |
| "eoc_token": "<channel|>", | |
| "eoi_token": "<image|>", | |
| "eos_token": "<turn|>", | |
| "eot_token": "<turn|>", | |
| "escape_token": "<|\"|>", | |
| "etc_token": "<tool_call|>", | |
| "etd_token": "<tool|>", | |
| "etr_token": "<tool_response|>", | |
| "extra_special_tokens": [ | |
| "<|video|>" | |
| ], | |
| "image_token": "<|image|>", | |
| "is_local": false, | |
| "mask_token": "<mask>", | |
| "model_max_length": 131072, | |
| "model_specific_special_tokens": { | |
| "audio_token": "<|audio|>", | |
| "boa_token": "<|audio>", | |
| "boi_token": "<|image>", | |
| "eoa_token": "<audio|>", | |
| "eoc_token": "<channel|>", | |
| "eoi_token": "<image|>", | |
| "eot_token": "<turn|>", | |
| "escape_token": "<|\"|>", | |
| "etc_token": "<tool_call|>", | |
| "etd_token": "<tool|>", | |
| "etr_token": "<tool_response|>", | |
| "image_token": "<|image|>", | |
| "soc_token": "<|channel>", | |
| "sot_token": "<|turn>", | |
| "stc_token": "<|tool_call>", | |
| "std_token": "<|tool>", | |
| "str_token": "<|tool_response>", | |
| "think_token": "<|think|>" | |
| }, | |
| "pad_token": "<pad>", | |
| "padding_side": "right", | |
| "processor_class": "Gemma4Processor", | |
| "response_schema": { | |
| "properties": { | |
| "content": { | |
| "type": "string" | |
| }, | |
| "role": { | |
| "const": "assistant" | |
| }, | |
| "thinking": { | |
| "type": "string" | |
| }, | |
| "tool_calls": { | |
| "items": { | |
| "properties": { | |
| "function": { | |
| "properties": { | |
| "arguments": { | |
| "additionalProperties": {}, | |
| "type": "object", | |
| "x-parser": "gemma4-tool-call" | |
| }, | |
| "name": { | |
| "type": "string" | |
| } | |
| }, | |
| "type": "object", | |
| "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})" | |
| }, | |
| "type": { | |
| "const": "function" | |
| } | |
| }, | |
| "type": "object" | |
| }, | |
| "type": "array", | |
| "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>" | |
| } | |
| }, | |
| "type": "object", | |
| "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?" | |
| }, | |
| "soc_token": "<|channel>", | |
| "sot_token": "<|turn>", | |
| "stc_token": "<|tool_call>", | |
| "std_token": "<|tool>", | |
| "str_token": "<|tool_response>", | |
| "think_token": "<|think|>", | |
| "tokenizer_class": "GemmaTokenizer", | |
| "unk_token": "<unk>" | |
| } | |