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-PreviewUse 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-PreviewBuild 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-PreviewUse Docker
docker model run hf.co/Sethblocks/Slime-PreviewYAML 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
We're not able to determine the quantization variants.
Install (macOS, Linux)
# 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