---
base_model: ibm-granite/granite-3.0-2b-instruct
library_name: transformers
fine_tuning: LORA
datasets: hawky-fb-marketing-hooks
license: other
tags:
- llama-cpp
- ibm
- ibm-granite
- ibm-granite-2B
- GGUF


---
# Sri-Vigneshwar-DJ/ibm-granite-3.0-2b-GGUF
This model was converted to GGUF format from [`granite-3.0-2b-instruct`](https://huggingface.co/ibm-granite/granite-3.0-2b-instruct) using llama.cpp
Refer to the [original model card](https://huggingface.co/granite-3.0-2b-instruct) for more details on the model.

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

```bash
brew install llama.cpp or !git clone https://github.com/ggerganov/llama.cpp.git

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

or 

### CLI:
```bash
! /content/llama.cpp/llama-cli -m ./quantized_model/FP16.gguf/ibm-granite-3.0-2b-GGUF -n 90 --repeat_penalty 1.0 --color -i -r "User:" -f /content/llama.cpp/prompts/chat-with-bob.txt

or

llama-cli --hf-repo Sri-Vigneshwar-DJ/ibm-granite-3.0-2b-GGUF --hf-file FP16.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo Sri-Vigneshwar-DJ/ibm-granite-3.0-2b-GGUF --hf-file FP8.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 or ''!make GGML_OPENBLAS=1' along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make

or

!make GGML_OPENBLAS=1
```

Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Sri-Vigneshwar-DJ/ibm-granite-3.0-2b-GGUF --hf-file FP8.gguf -p "Hi, Generate a detailed insight on 2024 Meta Campaigns"
```
or 
```
./llama-server --hf-repo Sri-Vigneshwar-DJ/ibm-granite-3.0-2b-GGUF --hf-file sFP8.gguf -c 2048
```