Instructions to use Gurubot/VaryTales-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Gurubot/VaryTales-8b 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 Gurubot/VaryTales-8b:Q4_K_M # Run inference directly in the terminal: llama cli -hf Gurubot/VaryTales-8b:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Gurubot/VaryTales-8b:Q4_K_M # Run inference directly in the terminal: llama cli -hf Gurubot/VaryTales-8b: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 Gurubot/VaryTales-8b:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Gurubot/VaryTales-8b: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 Gurubot/VaryTales-8b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Gurubot/VaryTales-8b:Q4_K_M
Use Docker
docker model run hf.co/Gurubot/VaryTales-8b:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Gurubot/VaryTales-8b with Ollama:
ollama run hf.co/Gurubot/VaryTales-8b:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Gurubot/VaryTales-8b with Docker Model Runner:
docker model run hf.co/Gurubot/VaryTales-8b:Q4_K_M
- Lemonade
How to use Gurubot/VaryTales-8b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Gurubot/VaryTales-8b:Q4_K_M
Run and chat with the model
lemonade run user.VaryTales-8b-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Gurubot/VaryTales-8b:Q4_K_M# Run inference directly in the terminal:
llama cli -hf Gurubot/VaryTales-8b:Q4_K_MUse 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 Gurubot/VaryTales-8b:Q4_K_M# Run inference directly in the terminal:
./llama-cli -hf Gurubot/VaryTales-8b:Q4_K_MBuild 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 Gurubot/VaryTales-8b:Q4_K_M# Run inference directly in the terminal:
./build/bin/llama-cli -hf Gurubot/VaryTales-8b:Q4_K_MUse Docker
docker model run hf.co/Gurubot/VaryTales-8b:Q4_K_MVary Tales 8b (uncensored)
A wider variety of names, places and stories.
Tired of seeing the same character names and settings in AI-generated content? Noticed how Emily Taylor, Elara Vance, and Maria Rodriguez seem to appear everywhere, often in the same places over and over like "Neo-Tokyo"? Vary Tales offers a broader range of character names, locations, and story concepts, bringing fresh variety to AI storytelling.
Examples of repeating names
Normal LLama:
Vary Tales:
This model is suitable for fiction and RP uses. It is uncensored (abliterated).
I focussed on extra variety for names, places and some common phrases in this model but I know there are more to address, if you like what I'm doing with this then let me know and I can refine it further.
- Downloads last month
- 195



Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf Gurubot/VaryTales-8b:Q4_K_M# Run inference directly in the terminal: llama cli -hf Gurubot/VaryTales-8b:Q4_K_M