GGUF
How to use from
llama.cpp
Install from brew
brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vdpappu/gemma2_coding_assistant_gguf
# Run inference directly in the terminal:
llama-cli -hf vdpappu/gemma2_coding_assistant_gguf
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vdpappu/gemma2_coding_assistant_gguf
# Run inference directly in the terminal:
llama-cli -hf vdpappu/gemma2_coding_assistant_gguf
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 vdpappu/gemma2_coding_assistant_gguf
# Run inference directly in the terminal:
./llama-cli -hf vdpappu/gemma2_coding_assistant_gguf
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 vdpappu/gemma2_coding_assistant_gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vdpappu/gemma2_coding_assistant_gguf
Use Docker
docker model run hf.co/vdpappu/gemma2_coding_assistant_gguf
Quick Links

Usage

from llama_cpp import Llama
from typing import Optional
import time
from huggingface_hub import hf_hub_download

def generate_prompt(input_text: str, instruction: Optional[str] = None) -> str:
    text = f"### Question: {input_text}\n\n### Answer: "
    if instruction:
        text = f"### Instruction: {instruction}\n\n{text}"
    return text

# Set up the parameters
repo_id = "vdpappu/gemma2_coding_assistant_gguf"
filename = "gemma2_coding.gguf"
local_dir = "."

downloaded_file_path = hf_hub_download(repo_id=repo_id, filename=filename, local_dir=local_dir)
print(f"File downloaded to: {downloaded_file_path}")

# Load the model 
llm = Llama(model_path=downloaded_file_path) #1 is thug
question = "Develop a Python program to clearly understand the concept of recursion."
prompt = generate_prompt(input_text=question)

start = time.time()
output = llm(prompt, 
             temperature=0.7,
             top_p=0.9,
             top_k=50,
             repeat_penalty=1.5,
             max_tokens=200, 
             stop=["Question:","<eos>"])
end = time.time()
print(f"Inference time: {end-start:.2f} seconds \n")
print(output['choices'][0]['text'])
Downloads last month
31
GGUF
Model size
3B params
Architecture
gemma
Hardware compatibility
Log In to add your hardware

We're not able to determine the quantization variants.

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train vdpappu/gemma2_coding_assistant_gguf