> :warning: This project has been renamed from `llama-cli` to `LocalAI` to reflect the fact that we are focusing on a fast drop-in OpenAI API rather on the CLI interface. We think that there are already many projects that can be used as a CLI interface already, for instance [llama.cpp](https://github.com/ggerganov/llama.cpp) and [gpt4all](https://github.com/nomic-ai/gpt4all). If you are were using `llama-cli` for CLI interactions and want to keep using it, use older versions or please open up an issue - contributions are welcome!
llama-cli is a straightforward, drop-in replacement API compatible with OpenAI for local CPU inferencing, based on [llama.cpp](https://github.com/ggerganov/llama.cpp), [gpt4all](https://github.com/nomic-ai/gpt4all) and [ggml](https://github.com/ggerganov/ggml), including support GPT4ALL-J which is Apache 2.0 Licensed and can be used for commercial purposes.
LocalAI is a straightforward, drop-in replacement API compatible with OpenAI for local CPU inferencing, based on [llama.cpp](https://github.com/ggerganov/llama.cpp), [gpt4all](https://github.com/nomic-ai/gpt4all) and [ggml](https://github.com/ggerganov/ggml), including support GPT4ALL-J which is Apache 2.0 Licensed and can be used for commercial purposes.
- OpenAI compatible API
- OpenAI compatible API
- Supports multiple-models
- Supports multiple-models
@ -18,12 +19,15 @@ Note: You might need to convert older models to the new format, see [here](https
## Usage
## Usage
The easiest way to run llama-cli is by using `docker-compose`:
> `LocalAI` comes by default as a container image. You can check out all the available images with corresponding tags [here](https://quay.io/repository/go-skynet/local-ai?tab=tags&tag=latest).
The easiest way to run LocalAI is by using `docker-compose`:
Note: The API doesn't inject a default prompt for talking to the model, while the CLI does. You have to use a prompt similar to what's described in the standford-alpaca docs: https://github.com/tatsu-lab/stanford_alpaca#data-release.
## Prompt templates
The API doesn't inject a default prompt for talking to the model. You have to use a prompt similar to what's described in the standford-alpaca docs: https://github.com/tatsu-lab/stanford_alpaca#data-release.
<details>
You can use a default template for every model present in your model path, by creating a corresponding file with the `.tmpl` suffix next to your model. For instance, if the model is called `foo.bin`, you can create a sibiling file, `foo.bin.tmpl` which will be used as a default prompt, for instance this can be used with alpaca:
You can use a default template for every model present in your model path, by creating a corresponding file with the `.tmpl` suffix next to your model. For instance, if the model is called `foo.bin`, you can create a sibiling file, `foo.bin.tmpl` which will be used as a default prompt, for instance this can be used with alpaca:
```
```
@ -58,70 +65,19 @@ Below is an instruction that describes a task. Write a response that appropriate
### Response:
### Response:
```
```
See the [prompt-templates](https://github.com/go-skynet/llama-cli/tree/master/prompt-templates) directory in this repository for templates for most popular models.
See the [prompt-templates](https://github.com/go-skynet/LocalAI/tree/master/prompt-templates) directory in this repository for templates for most popular models.
## Container images
`llama-cli` comes by default as a container image. You can check out all the available images with corresponding tags [here](https://quay.io/repository/go-skynet/llama-cli?tab=tags&tag=latest)
To begin, run:
```
docker run -ti --rm quay.io/go-skynet/llama-cli:latest --instruction "What's an alpaca?" --topk 10000 --model ...
```
Where `--model` is the path of the model you want to use.
Note: you need to mount a volume to the docker container in order to load a model, for instance:
```
# assuming your model is in /path/to/your/models/foo.bin
docker run -v /path/to/your/models:/models -ti --rm quay.io/go-skynet/llama-cli:latest --instruction "What's an alpaca?" --topk 10000 --model /models/foo.bin
```
You will receive a response like the following:
```
An alpaca is a member of the South American Camelid family, which includes the llama, guanaco and vicuña. It is a domesticated species that originates from the Andes mountain range in South America. Alpacas are used in the textile industry for their fleece, which is much softer than wool. Alpacas are also used for meat, milk, and fiber.
```
## Basic usage
</details>
To use llama-cli, specify a pre-trained GPT-based model, an input text, and an instruction for text generation. llama-cli takes the following arguments when running from the CLI:
llama-cli --model ~/ggml-alpaca-7b-q4.bin --instruction "What's an alpaca?"
```
This will generate text based on the given model and instruction.
## API
## API
`llama-cli` also provides an API for running text generation as a service. The models once loaded the first time will be kept in memory.
`LocalAI` provides an API for running text generation as a service, that follows the OpenAI reference and can be used as a drop-in. The models once loaded the first time will be kept in memory.
<details>
Example of starting the API with `docker`:
Example of starting the API with `docker`:
```bash
```bash
docker run -p 8080:8080 -ti --rm quay.io/go-skynet/llama-cli:latest api --models-path /path/to/models --context-size 700 --threads 4
echo"An Alpaca (Vicugna pacos) is a domesticated species of South American camelid, related to llamas and originally from Peru but now found throughout much of Andean region. They are bred for their fleeces which can be spun into wool or knitted items such as hats, sweaters, blankets etc"|llama-cli--model~/ggml-alpaca-7b-q4.bin--instruction"Proofread, improving clarity and flow"--input"-"