|
--- |
|
inference: false |
|
license: other |
|
model_type: llama |
|
--- |
|
# Meta's LLaMA 7B - AWQ GGUF |
|
These files are in GGUF format. |
|
- Model creator: [Meta](https://huggingface.co/none) |
|
- Original model: [LLaMA 7B](https://ai.meta.com/blog/large-language-model-llama-meta-ai) |
|
|
|
The model was converted by the combination of [llama.cpp](https://github.com/ggerganov/llama.cpp) and quantization method [AWQ](https://github.com/mit-han-lab/llm-awq) |
|
|
|
## How to use models in `llama.cpp` |
|
|
|
``` |
|
./main -m ggml-model-q4_0-awq.gguf -n 128 --prompt "Once upon a time" |
|
``` |
|
Please refer to the instructions at the [PR](https://github.com/ggerganov/llama.cpp/pull/4593) |
|
|
