Instructions to use ClaireLee2429/gemma-2b-recipes-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ClaireLee2429/gemma-2b-recipes-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ClaireLee2429/gemma-2b-recipes-gguf",
	filename="model.q4_k_m.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ClaireLee2429/gemma-2b-recipes-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ClaireLee2429/gemma-2b-recipes-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ClaireLee2429/gemma-2b-recipes-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ClaireLee2429/gemma-2b-recipes-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ClaireLee2429/gemma-2b-recipes-gguf:Q4_K_M

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 ClaireLee2429/gemma-2b-recipes-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ClaireLee2429/gemma-2b-recipes-gguf:Q4_K_M

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 ClaireLee2429/gemma-2b-recipes-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ClaireLee2429/gemma-2b-recipes-gguf:Q4_K_M

Use Docker

docker model run hf.co/ClaireLee2429/gemma-2b-recipes-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use ClaireLee2429/gemma-2b-recipes-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ClaireLee2429/gemma-2b-recipes-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ClaireLee2429/gemma-2b-recipes-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ClaireLee2429/gemma-2b-recipes-gguf:Q4_K_M

Ollama
How to use ClaireLee2429/gemma-2b-recipes-gguf with Ollama:
```
ollama run hf.co/ClaireLee2429/gemma-2b-recipes-gguf:Q4_K_M
```

Unsloth Studio

How to use ClaireLee2429/gemma-2b-recipes-gguf 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 ClaireLee2429/gemma-2b-recipes-gguf 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 ClaireLee2429/gemma-2b-recipes-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ClaireLee2429/gemma-2b-recipes-gguf to start chatting

Docker Model Runner
How to use ClaireLee2429/gemma-2b-recipes-gguf with Docker Model Runner:
```
docker model run hf.co/ClaireLee2429/gemma-2b-recipes-gguf:Q4_K_M
```

Lemonade

How to use ClaireLee2429/gemma-2b-recipes-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ClaireLee2429/gemma-2b-recipes-gguf:Q4_K_M

Run and chat with the model

lemonade run user.gemma-2b-recipes-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

Gemma-2B Recipes (GGUF Q4_K_M)

Quantized GGUF version of google/gemma-2b fine-tuned on recipe data for recipe generation.

Model Details


Base model	google/gemma-2b
LoRA adapter	ClaireLee2429/gemma-2b-recipes-lora
Training data	corbt/all-recipes
Quantization	Q4_K_M (4-bit, K-means)
File size	~1.5 GB
Context length	8192 tokens
Format	GGUF (llama.cpp compatible)

How It Was Made

Fine-tuned Gemma-2B on recipe data using LoRA (see recipe-lm)
Merged LoRA adapter into base model weights
Converted to GGUF FP16 using convert_hf_to_gguf.py from llama.cpp
Quantized to Q4_K_M using llama-quantize

Usage

With llama-cpp-python

from huggingface_hub import hf_hub_download
from llama_cpp import Llama

model_path = hf_hub_download(
    repo_id="ClaireLee2429/gemma-2b-recipes-gguf",
    filename="model.q4_k_m.gguf",
)

llm = Llama(model_path=model_path, n_threads=8, n_ctx=2048)

output = llm.create_completion(
    "Recipe for chocolate chip cookies:\n",
    max_tokens=256,
    temperature=0.7,
    top_p=0.9,
    repeat_penalty=1.2,
)

print(output["choices"][0]["text"])

With llama.cpp CLI

./llama-cli -m model.q4_k_m.gguf -p "Recipe for pasta carbonara:" -n 256

Example Output

Recipe for chocolate chip cookies:
- 1/2 cup butter
- 1/3 cup sugar
- 1 egg
- 1/4 teaspoon vanilla
- 2/3 cup white flour
- 1/3 cup all-purpose flour
- 1/8 teaspoon baking soda
- 1/8 teaspoon salt
- 1/2 teaspoon cinnamon
- 1/4 cup chocolate chips

Directions:
- Sift together the flours.
- Add in salt and baking powder and mix.
- Add in vanilla, egg and sugar and mix well.
- Roll out on a lightly floured board and cut into desired shapes
  and place on an ungreased cookie sheet.
- Bake at 375 degrees for 10-12 minutes.

Performance

Benchmarked on Apple M-series (Metal) and estimated for CPU-only server:

Environment	Time to first token	Tokens/sec
Apple Silicon (Metal)	~0.1s	~90 tok/s
8 vCPU server (CPU only)	~1-2s	~10-20 tok/s

Training pipeline & server: glee2429/recipe-lm
Web frontend: glee2429/kitchen-genie
Live demo: ClaireLee2429/recipe-lm-api (HuggingFace Space)

Downloads last month: 11

GGUF

Model size

3B params

Architecture

gemma

Hardware compatibility

4-bit

Model tree for ClaireLee2429/gemma-2b-recipes-gguf

Base model

google/gemma-2b

Adapter

(23696)

this model

ClaireLee2429
/

gemma-2b-recipes-gguf