---
language:
- en
- zh
license: apache-2.0
tags:
- llm
- llama-cpp
- gguf-my-repo
base_model: duoqi/Nanbeige2-16B-Chat
pipeline_tag: text-generation
---

# NikolayKozloff/Nanbeige2-16B-Chat-Q5_K_S-GGUF
This model was converted to GGUF format from [`duoqi/Nanbeige2-16B-Chat`](https://huggingface.co/duoqi/Nanbeige2-16B-Chat) 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/duoqi/Nanbeige2-16B-Chat) 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 --hf-repo NikolayKozloff/Nanbeige2-16B-Chat-Q5_K_S-GGUF --hf-file nanbeige2-16b-chat-q5_k_s.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo NikolayKozloff/Nanbeige2-16B-Chat-Q5_K_S-GGUF --hf-file nanbeige2-16b-chat-q5_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.
```
./main --hf-repo NikolayKozloff/Nanbeige2-16B-Chat-Q5_K_S-GGUF --hf-file nanbeige2-16b-chat-q5_k_s.gguf -p "The meaning to life and the universe is"
```
or 
```
./server --hf-repo NikolayKozloff/Nanbeige2-16B-Chat-Q5_K_S-GGUF --hf-file nanbeige2-16b-chat-q5_k_s.gguf -c 2048
```