README.md

---
base_model: SzilviaB/Magnum_Backyard_Party_12b
library_name: transformers
tags:
- mergekit
- merge
- llama-cpp
- gguf-my-repo
---

# Triangle104/Magnum_Backyard_Party_12b-Q4_K_M-GGUF
This model was converted to GGUF format from [`SzilviaB/Magnum_Backyard_Party_12b`](https://huggingface.co/SzilviaB/Magnum_Backyard_Party_12b) 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/SzilviaB/Magnum_Backyard_Party_12b) for more details on the model.

Model details:
-
This is a merge of pre-trained language models created using mergekit.

Merge Method
-
This model was merged using the SLERP merge method.
Models Merged

The following models were included in the merge:

    Sao10K/MN-BackyardAI-Party-12B-v1
    anthracite-org/magnum-v4-12b

Configuration
-
The following YAML configuration was used to produce this model:

models:
  - model: anthracite-org/magnum-v4-12b
  - model: Sao10K/MN-BackyardAI-Party-12B-v1
merge_method: slerp
base_model: anthracite-org/magnum-v4-12b
dtype: bfloat16
parameters:
  t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers

---
## 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 Triangle104/Magnum_Backyard_Party_12b-Q4_K_M-GGUF --hf-file magnum_backyard_party_12b-q4_k_m.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo Triangle104/Magnum_Backyard_Party_12b-Q4_K_M-GGUF --hf-file magnum_backyard_party_12b-q4_k_m.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 Triangle104/Magnum_Backyard_Party_12b-Q4_K_M-GGUF --hf-file magnum_backyard_party_12b-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo Triangle104/Magnum_Backyard_Party_12b-Q4_K_M-GGUF --hf-file magnum_backyard_party_12b-q4_k_m.gguf -c 2048
```