---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- llama-cpp
- gguf-my-lora
base_model: vinhnx90/llama-3-8b-bnb-4bit
datasets:
- yahma/alpaca-cleaned
---

# vinhnx90/llama-3-8b-bnb-4bit-F16-GGUF
This LoRA adapter was converted to GGUF format from [`vinhnx90/llama-3-8b-bnb-4bit`](https://huggingface.co/vinhnx90/llama-3-8b-bnb-4bit) via the ggml.ai's [GGUF-my-lora](https://huggingface.co/spaces/ggml-org/gguf-my-lora) space.
Refer to the [original adapter repository](https://huggingface.co/vinhnx90/llama-3-8b-bnb-4bit) for more details.

## Use with llama.cpp

```bash
# with cli
llama-cli -m base_model.gguf --lora llama-3-8b-bnb-4bit-f16.gguf (...other args)

# with server
llama-server -m base_model.gguf --lora llama-3-8b-bnb-4bit-f16.gguf (...other args)
```

To know more about LoRA usage with llama.cpp server, refer to the [llama.cpp server documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/server/README.md).