---
base_model: RyanYr/llama32-3b-it_CoT-it_SFT_BoN_iter1
library_name: transformers
model_name: llama32-3b-it_CoT-it_SFT_BoN_iter1
tags:
- generated_from_trainer
- trl
- sft
- llama-cpp
- text-generation-inference
licence: license
license: mit
---

# Devarui379/llama32-3b-it_CoT-it_SFT_BoN_iter1-Q8_0-GGUF
This model was converted to GGUF format
Refer to the [original model card](https://huggingface.co/RyanYr/llama32-3b-it_CoT-it_SFT_BoN_iter1) 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 Devarui379/llama32-3b-it_CoT-it_SFT_BoN_iter1-Q8_0-GGUF --hf-file llama32-3b-it_cot-it_sft_bon_iter1-q8_0.gguf -p "The meaning to life and the universe is"
```

### Server:
```bash
llama-server --hf-repo Devarui379/llama32-3b-it_CoT-it_SFT_BoN_iter1-Q8_0-GGUF --hf-file llama32-3b-it_cot-it_sft_bon_iter1-q8_0.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 Devarui379/llama32-3b-it_CoT-it_SFT_BoN_iter1-Q8_0-GGUF --hf-file llama32-3b-it_cot-it_sft_bon_iter1-q8_0.gguf -p "The meaning to life and the universe is"
```
or 
```
./llama-server --hf-repo Devarui379/llama32-3b-it_CoT-it_SFT_BoN_iter1-Q8_0-GGUF --hf-file llama32-3b-it_cot-it_sft_bon_iter1-q8_0.gguf -c 2048
```