---
license: apache-2.0
language:
- si
- en
base_model: manthilaffs/Gamunu-4B-Instruct-Alpha
pipeline_tag: text-generation
tags:
- instruction-following
- NLP
- question-answering
- reasoning
- academic
- LK
- llama-cpp
---

# manthilaffs/Gamunu-4B-Instruct-Alpha-GGUF
These models was converted to GGUF format from [`manthilaffs/Gamunu-4B-Instruct-Alpha`](https://huggingface.co/manthilaffs/Gamunu-4B-Instruct-Alpha) using llama.cpp.
Refer to the [original model card](https://huggingface.co/manthilaffs/Gamunu-4B-Instruct-Alpha) 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 manthilaffs/Gamunu-4B-Instruct-Alpha-GGUF --hf-file gamunu-4b-instruct-alpha-BF16.gguf -p "Hello! how are you?"
```
```bash
llama-cli --hf-repo manthilaffs/Gamunu-4B-Instruct-Alpha-GGUF --hf-file gamunu-4b-instruct-alpha-q8_0.gguf -p "Hello! how are you?"
```

### Server:
```bash
llama-server --hf-repo manthilaffs/Gamunu-4B-Instruct-Alpha-GGUF --hf-file gamunu-4b-instruct-alpha-BF16.gguf -c 2048
```
```bash
llama-server --hf-repo manthilaffs/Gamunu-4B-Instruct-Alpha-GGUF --hf-file gamunu-4b-instruct-alpha-q8_0.gguf -c 2048
```