---
base_model: mergekit-community/mergekit-slerp-anaazls
library_name: transformers
tags:
- mergekit
- merge
- llama-cpp
- gguf-my-repo
---
![image/png](/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F660db7a88ff269c4e4381860%2F5Hlws4GYlIPBaEGUbNclY.png)

Like MagnumSmaug ( https://huggingface.co/SzilviaB/Magnum_Smaug-Q4_K_M-GGUF )

But more practical and direct, not nearly as shy or prude.

Objects far less than MagnumSmaug, pretty much down for anything, and can be naughty.

# SzilviaB/Smaug_Magnum_34b-Q3_K_S-GGUF

Slerp merge of
abacusai/Smaug-34B-v0.1 (Base)

anthracite-org/magnum-v3-34b

# SzilviaB/mergekit-slerp-anaazls-Q3_K_S-GGUF
This model was converted to GGUF format from [`mergekit-community/mergekit-slerp-anaazls`](https://huggingface.co/mergekit-community/mergekit-slerp-anaazls) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/mergekit-community/mergekit-slerp-anaazls) for more details on the model.

## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)

```bash
brew install llama.cpp

```
Invoke the llama.cpp server or the CLI.

### CLI:
```bash
llama-cli --hf-repo SzilviaB/mergekit-slerp-anaazls-Q3_K_S-GGUF --hf-file mergekit-slerp-anaazls-q3_k_s.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo SzilviaB/mergekit-slerp-anaazls-Q3_K_S-GGUF --hf-file mergekit-slerp-anaazls-q3_k_s.gguf -c 2048
```

Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```

Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```

Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo SzilviaB/mergekit-slerp-anaazls-Q3_K_S-GGUF --hf-file mergekit-slerp-anaazls-q3_k_s.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo SzilviaB/mergekit-slerp-anaazls-Q3_K_S-GGUF --hf-file mergekit-slerp-anaazls-q3_k_s.gguf -c 2048
```