Instructions to use Acvarius-AI/GhostLlama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Acvarius-AI/GhostLlama with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Acvarius-AI/GhostLlama", filename="ghostllama.Q4_K_M.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use Acvarius-AI/GhostLlama with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Acvarius-AI/GhostLlama:Q4_K_M # Run inference directly in the terminal: llama-cli -hf Acvarius-AI/GhostLlama:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Acvarius-AI/GhostLlama:Q4_K_M # Run inference directly in the terminal: llama-cli -hf Acvarius-AI/GhostLlama: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 Acvarius-AI/GhostLlama:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Acvarius-AI/GhostLlama: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 Acvarius-AI/GhostLlama:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Acvarius-AI/GhostLlama:Q4_K_M
Use Docker
docker model run hf.co/Acvarius-AI/GhostLlama:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Acvarius-AI/GhostLlama with Ollama:
ollama run hf.co/Acvarius-AI/GhostLlama:Q4_K_M
- Unsloth Studio new
How to use Acvarius-AI/GhostLlama 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 Acvarius-AI/GhostLlama 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 Acvarius-AI/GhostLlama to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Acvarius-AI/GhostLlama to start chatting
- Docker Model Runner
How to use Acvarius-AI/GhostLlama with Docker Model Runner:
docker model run hf.co/Acvarius-AI/GhostLlama:Q4_K_M
- Lemonade
How to use Acvarius-AI/GhostLlama with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Acvarius-AI/GhostLlama:Q4_K_M
Run and chat with the model
lemonade run user.GhostLlama-Q4_K_M
List all available models
lemonade list
Upload install.sh with huggingface_hub
Browse files- install.sh +124 -0
install.sh
ADDED
|
@@ -0,0 +1,124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/bin/bash
|
| 2 |
+
|
| 3 |
+
# Colors
|
| 4 |
+
PURPLE='\033[0;35m'
|
| 5 |
+
TEAL='\033[0;36m'
|
| 6 |
+
NC='\033[0m'
|
| 7 |
+
|
| 8 |
+
echo ' ... ...'
|
| 9 |
+
echo ' -*%##: .=#=.'
|
| 10 |
+
echo ' *# ##=::=###:'
|
| 11 |
+
echo ' -%# ## ## ###:'
|
| 12 |
+
echo ' .=# ########## .'
|
| 13 |
+
echo ' :# ## ##### #+'
|
| 14 |
+
echo ' .= #############+.'
|
| 15 |
+
echo ' .## ##### ### #+###.'
|
| 16 |
+
echo ' .# ####### ###.'
|
| 17 |
+
echo ' .# #############=.'
|
| 18 |
+
echo ' :## ########%*'
|
| 19 |
+
echo ' :# ######## ##*'
|
| 20 |
+
echo ' ...........:=########### #:'
|
| 21 |
+
echo ' .....:+ ####################### #.'
|
| 22 |
+
echo ' .:= # ########################### #:'
|
| 23 |
+
echo ' .=# # ########################### #=.'
|
| 24 |
+
echo ' ...:+ # ############################# ##.'
|
| 25 |
+
echo ' :=# # # ############################# ##.'
|
| 26 |
+
echo ' ....:=# ############################ ##.'
|
| 27 |
+
echo ' :# ########################## ##=.'
|
| 28 |
+
echo ' .=# ########################## #-'
|
| 29 |
+
echo ' *# ########################### #'
|
| 30 |
+
echo ' * ##### # ########## #='
|
| 31 |
+
echo ' =# #### # ######## #'
|
| 32 |
+
echo ' * ##### # ###### # #+.'
|
| 33 |
+
echo ' * ###### #%- =# ####### @'
|
| 34 |
+
echo ' .:= ##===###=- .= ###### #=-'
|
| 35 |
+
echo ' .=# ##=. :%+: .=# #===# %*'
|
| 36 |
+
echo ' .+:... .##=:: ....'
|
| 37 |
+
echo ' ...'
|
| 38 |
+
|
| 39 |
+
# Header
|
| 40 |
+
echo -e "${PURPLE}"
|
| 41 |
+
echo "ββββββββββββββββββββββββββββββββββββββββ"
|
| 42 |
+
echo "β π» GhostLlama INSTALLER v1.0 β"
|
| 43 |
+
echo "β π How to Sacrifice your Llama β"
|
| 44 |
+
echo "ββββββββββββββββββββββββββββββββββββββββ"
|
| 45 |
+
echo -e "${NC}"
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
# Create directories
|
| 52 |
+
echo -e "${TEAL}[π£] Preparing the altar...${NC}"
|
| 53 |
+
mkdir -p ~/ghostllama/models
|
| 54 |
+
mkdir -p ~/ghostllama/config
|
| 55 |
+
|
| 56 |
+
# Download model
|
| 57 |
+
echo -e "${TEAL}[π£] Summoning the spirit from HuggingFace...${NC}"
|
| 58 |
+
cd ~/ghostllama/models
|
| 59 |
+
wget -O ghostllama.Q4_K_M.gguf https://huggingface.co/Aquarius-AI/GhostLlama/resolve/main/ghostllama.Q4_K_M.gguf
|
| 60 |
+
|
| 61 |
+
# Telegram setup
|
| 62 |
+
echo -e "${TEAL}[π£] Connect to Telegram? (y/n)${NC}"
|
| 63 |
+
read -r telegram
|
| 64 |
+
|
| 65 |
+
if [ "$telegram" = "y" ]; then
|
| 66 |
+
echo -e "${TEAL}[π£] Enter your Telegram Bot Token:${NC}"
|
| 67 |
+
read -r token
|
| 68 |
+
echo "TELEGRAM_BOT_TOKEN=$token" > ~/ghostllama/config/telegram.conf
|
| 69 |
+
|
| 70 |
+
# Create basic bot script
|
| 71 |
+
cat > ~/ghostllama/telegram-bot.py << 'EOF'
|
| 72 |
+
import requests
|
| 73 |
+
import subprocess
|
| 74 |
+
import time
|
| 75 |
+
|
| 76 |
+
TOKEN = open(os.path.expanduser('~/ghostllama/config/telegram.conf')).read().split('=')[1].strip()
|
| 77 |
+
URL = f"https://api.telegram.org/bot{TOKEN}"
|
| 78 |
+
|
| 79 |
+
def get_updates(offset=None):
|
| 80 |
+
url = f"{URL}/getUpdates"
|
| 81 |
+
params = {"timeout": 100, "offset": offset}
|
| 82 |
+
response = requests.get(url, params=params)
|
| 83 |
+
return response.json()
|
| 84 |
+
|
| 85 |
+
def send_message(chat_id, text):
|
| 86 |
+
url = f"{URL}/sendMessage"
|
| 87 |
+
params = {"chat_id": chat_id, "text": text}
|
| 88 |
+
requests.post(url, params=params)
|
| 89 |
+
|
| 90 |
+
def call_model(prompt):
|
| 91 |
+
result = subprocess.run(
|
| 92 |
+
["~/llama.cpp/build/bin/llama-cli", "-m", "~/ghostllama/models/ghostllama.Q4_K_M.gguf", "-p", prompt, "-n", "50"],
|
| 93 |
+
capture_output=True, text=True
|
| 94 |
+
)
|
| 95 |
+
return result.stdout
|
| 96 |
+
|
| 97 |
+
last_update = 0
|
| 98 |
+
while True:
|
| 99 |
+
updates = get_updates(last_update + 1)
|
| 100 |
+
if "result" in updates:
|
| 101 |
+
for update in updates["result"]:
|
| 102 |
+
last_update = update["update_id"]
|
| 103 |
+
if "message" in update and "text" in update["message"]:
|
| 104 |
+
chat_id = update["message"]["chat"]["id"]
|
| 105 |
+
user_text = update["message"]["text"]
|
| 106 |
+
response = call_model(user_text)
|
| 107 |
+
send_message(chat_id, response)
|
| 108 |
+
time.sleep(1)
|
| 109 |
+
EOF
|
| 110 |
+
|
| 111 |
+
echo -e "${TEAL}[π£] Telegram configured! Run with: python ~/ghostllama/telegram-bot.py${NC}"
|
| 112 |
+
|
| 113 |
+
echo -e "${TEAL}[π£] Note: Telegram support is a placeholder in v1.0${NC}"
|
| 114 |
+
echo -e "${TEAL}[π£] The real bot will arrive in v1.1. Your token is saved for future use.${NC}"
|
| 115 |
+
|
| 116 |
+
fi
|
| 117 |
+
|
| 118 |
+
# Done
|
| 119 |
+
echo -e "${PURPLE}"
|
| 120 |
+
echo "ββββββββββββββββββββββββββββββββββββββββ"
|
| 121 |
+
echo "β β¨ SACRIFICE COMPLETE β¨ β"
|
| 122 |
+
echo "β Run 'cd ~/ghostllama' to begin β"
|
| 123 |
+
echo "ββββββββββββββββββββββββββββββββββββββββ"
|
| 124 |
+
echo -e "${NC}"
|