Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Doge-GPT/DogeGPT1-1B:# Run inference directly in the terminal:
llama-cli -hf Doge-GPT/DogeGPT1-1B: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 Doge-GPT/DogeGPT1-1B:# Run inference directly in the terminal:
./llama-cli -hf Doge-GPT/DogeGPT1-1B: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 Doge-GPT/DogeGPT1-1B:# Run inference directly in the terminal:
./build/bin/llama-cli -hf Doge-GPT/DogeGPT1-1B:Use Docker
docker model run hf.co/Doge-GPT/DogeGPT1-1B:DogeGPT Meme Coin 🐕🤖
The Meme Coin will be launched Soon Join our socials to find out more (and invest early🐕) All other DogeGPTs are all fake, only check the following socials for update Share them and mention us on X(twitter)
DogeGPT1-1B 🐕🤖
DogeGPT1-1B is an open-sourced 1.24B-parameter Large Language Model (LLM) designed to bring the fun of meme coins and the power of AI together! Built on the LLaMA architecture, DogeGPT is tailored for conversational AI applications with a playful twist. Whether you're a meme coin enthusiast, developer, or AI explorer, DogeGPT is here to spark your creativity.
3B and 8B -parameter LLMs will be annonced soon
Model Overview 🚀
- Model Name: DogeGPT1-1B
- Architecture: LLaMA
- Model Size: 1.24B parameters
- Quantization Formats: GGUF (2-bit, 3-bit, 4-bit, 5-bit, 6-bit, 8-bit)
- License: Apache 2.0
- Tags:
PyTorch,LLaMA,TRL,GGUF,conversational - Downloads Last Month: 115
Features 🌟
- Conversational AI: Perfect for building chatbots, virtual assistants, or meme-themed conversational models.
- Quantization Support: Includes efficient formats for deployment in resource-constrained environments.
- Open Source: Fully available under the permissive Apache 2.0 license.
Getting Started 🛠️
Installation
Clone the model and install the necessary dependencies:
pip install transformers huggingface_hub
Usage Example
Here’s how to load DogeGPT1-1B using transformers:
from transformers import AutoModelForCausalLM, AutoTokenizer
# Load the model and tokenizer
model = AutoModelForCausalLM.from_pretrained("Doge-GPT/DogeGPT1-1B")
tokenizer = AutoTokenizer.from_pretrained("Doge-GPT/DogeGPT1-1B")
# Generate text
input_text = "What is DogeGPT?"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
- Downloads last month
- 220
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Install from brew
# Start a local OpenAI-compatible server with a web UI: llama-server -hf Doge-GPT/DogeGPT1-1B:# Run inference directly in the terminal: llama-cli -hf Doge-GPT/DogeGPT1-1B: