How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Undi95/MXLewdMini-L2-13B-GGUF:# Run inference directly in the terminal:
llama cli -hf Undi95/MXLewdMini-L2-13B-GGUF: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 Undi95/MXLewdMini-L2-13B-GGUF:# Run inference directly in the terminal:
./llama-cli -hf Undi95/MXLewdMini-L2-13B-GGUF: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 Undi95/MXLewdMini-L2-13B-GGUF:# Run inference directly in the terminal:
./build/bin/llama-cli -hf Undi95/MXLewdMini-L2-13B-GGUF:Use Docker
docker model run hf.co/Undi95/MXLewdMini-L2-13B-GGUF:Quick Links
Merge:
[Xwin (0.66) + ReMM (0.33)] x [Xwin (0.33) + MLewd (0.66)]
The goal was to recreate https://huggingface.co/Undi95/MXLewd-L2-20B-GGUF in 13B without using merge interlacing (will probably be a little less good).
Models used
- Undi95/MLewd-L2-13B-v2-3
- Undi95/ReMM-v2.1-L2-13B
- Xwin-LM/Xwin-LM-13B-V0.1
One part is ReMM (0.33) and Xwin (0.66)
One part is Xwin (0.33) and MLewd (0.66)
Prompt template: Alpaca
Below is an instruction that describes a task. Write a response that completes the request.
### Instruction:
{prompt}
### Response:
- Downloads last month
- 25
Hardware compatibility
Log In to add your hardware
4-bit
5-bit
6-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf Undi95/MXLewdMini-L2-13B-GGUF:# Run inference directly in the terminal: llama cli -hf Undi95/MXLewdMini-L2-13B-GGUF: