Instructions to use Sethblocks/Slime-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sethblocks/Slime-Preview with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Sethblocks/Slime-Preview",
	filename="Slime-400e-stretch.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Sethblocks/Slime-Preview 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 Sethblocks/Slime-Preview
# Run inference directly in the terminal:
llama cli -hf Sethblocks/Slime-Preview

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Sethblocks/Slime-Preview
# Run inference directly in the terminal:
llama cli -hf Sethblocks/Slime-Preview

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 Sethblocks/Slime-Preview
# Run inference directly in the terminal:
./llama-cli -hf Sethblocks/Slime-Preview

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 Sethblocks/Slime-Preview
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Sethblocks/Slime-Preview

Use Docker

docker model run hf.co/Sethblocks/Slime-Preview

LM Studio
Jan
Ollama
How to use Sethblocks/Slime-Preview with Ollama:
```
ollama run hf.co/Sethblocks/Slime-Preview
```

Unsloth Studio

How to use Sethblocks/Slime-Preview 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 Sethblocks/Slime-Preview 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 Sethblocks/Slime-Preview to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Sethblocks/Slime-Preview to start chatting

Atomic Chat new
Docker Model Runner
How to use Sethblocks/Slime-Preview with Docker Model Runner:
```
docker model run hf.co/Sethblocks/Slime-Preview
```

Lemonade

How to use Sethblocks/Slime-Preview with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Sethblocks/Slime-Preview

Run and chat with the model

lemonade run user.Slime-Preview-{{QUANT_TAG}}

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Slime (Public Release)

This is my earliest model fine-tune, probably not great for much, I just made it for fun and to learn a little. This is based on Smollm2 360m and finetuned for more rp-style chat. Essentially, this is for research purposes, I wouldn't take this model too seriously.

Safety

This model tends to have lighter gaurd-rails than most, so it may produce dangerous or NSFW outputs. It also doesn't quite understand what it does and doesn't know, so a lot of responses may just be complete hallucinations.

This is currently only in gguf format, I have long since deleted the original weights from about 1 1/2 - 2 years ago.

Downloads last month: 2

GGUF

Model size

0.4B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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