---
license: llama3.2
datasets:
- scb10x/typhoon-t1-3b-research-preview-data
language:
- th
- en
base_model:
- scb10x/llama3.2-typhoon2-t1-3b-research-preview
pipeline_tag: text-generation
tags:
- llama-cpp
---

This is a GGUF format for [`scb10x/llama3.2-typhoon2-t1-3b-research-preview`](https://huggingface.co/scb10x/llama3.2-typhoon2-t1-3b-research-preview) using `llama.cpp`.

Please see the [original model card](https://huggingface.co/scb10x/llama3.2-typhoon2-t1-3b-research-preview) 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 scb10x/llama3.2-typhoon2-t1-3b-research-preview-gguf --hf-file llama3.2-typhoon2-t1-3b-q4_k_m.gguf -p "หากแปลคำว่า \"ไต้ฝุ่น\" เป็นภาษาอังกฤษ ในคำที่ถูกแปลแล้วจะมีตัวอักษร \"o\" ทั้งหมดกี่ตัว"
```

### Server:
```bash
llama-server --hf-repo scb10x/llama3.2-typhoon2-t1-3b-research-preview-gguf --hf-file llama3.2-typhoon2-t1-3b-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 scb10x/llama3.2-typhoon2-t1-3b-research-preview-gguf --hf-file llama3.2-typhoon2-t1-3b-q4_k_m.gguf -p "หากแปลคำว่า \"ไต้ฝุ่น\" เป็นภาษาอังกฤษ ในคำที่ถูกแปลแล้วจะมีตัวอักษร \"o\" ทั้งหมดกี่ตัว"
```

or 

```
./llama-server --hf-repo scb10x/llama3.2-typhoon2-t1-3b-research-preview-gguf --hf-file llama3.2-typhoon2-t1-3b-q4_k_m.gguf -c 2048
```