LocalAI supports generating text with GPT with llama.cpp and other backends (such as rwkv.cpp as ) see also the Model compatibility for an up-to-date list of the supported model families.

Note:

  • You can also specify the model name as part of the OpenAI token.
  • If only one model is available, the API will use it for all the requests.

API Reference

Chat completions

https://platform.openai.com/docs/api-reference/chat

For example, to generate a chat completion, you can send a POST request to the /v1/chat/completions endpoint with the instruction as the request body:

  curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
  "model": "ggml-koala-7b-model-q4_0-r2.bin",
  "messages": [{"role": "user", "content": "Say this is a test!"}],
  "temperature": 0.7
}'

Available additional parameters: top_p, top_k, max_tokens

Edit completions

https://platform.openai.com/docs/api-reference/edits

To generate an edit completion you can send a POST request to the /v1/edits endpoint with the instruction as the request body:

  curl http://localhost:8080/v1/edits -H "Content-Type: application/json" -d '{
  "model": "ggml-koala-7b-model-q4_0-r2.bin",
  "instruction": "rephrase",
  "input": "Black cat jumped out of the window",
  "temperature": 0.7
}'

Available additional parameters: top_p, top_k, max_tokens.

Completions

https://platform.openai.com/docs/api-reference/completions

To generate a completion, you can send a POST request to the /v1/completions endpoint with the instruction as per the request body:

  curl http://localhost:8080/v1/completions -H "Content-Type: application/json" -d '{
  "model": "ggml-koala-7b-model-q4_0-r2.bin",
  "prompt": "A long time ago in a galaxy far, far away",
  "temperature": 0.7
}'

Available additional parameters: top_p, top_k, max_tokens

List models

You can list all the models available with:

  curl http://localhost:8080/v1/models

Backends

AutoGPTQ

AutoGPTQ is an easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Prerequisites

This is an extra backend - in the container images is already available and there is nothing to do for the setup.

If you are building LocalAI locally, you need to install AutoGPTQ manually.

Model setup

The models are automatically downloaded from huggingface if not present the first time. It is possible to define models via YAML config file, or just by querying the endpoint with the huggingface repository model name. For example, create a YAML config file in models/:

  name: orca
backend: autogptq
model_base_name: "orca_mini_v2_13b-GPTQ-4bit-128g.no-act.order"
parameters:
  model: "TheBloke/orca_mini_v2_13b-GPTQ"
# ...

Test with:

  curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{                                                                                                         
   "model": "orca",
   "messages": [{"role": "user", "content": "How are you?"}],
   "temperature": 0.1
 }'

RWKV

A full example on how to run a rwkv model is in the examples.

Note: rwkv models needs to specify the backend rwkv in the YAML config files and have an associated tokenizer along that needs to be provided with it:

  36464540 -rw-r--r--  1 mudler mudler 1.2G May  3 10:51 rwkv_small
36464543 -rw-r--r--  1 mudler mudler 2.4M May  3 10:51 rwkv_small.tokenizer.json

llama.cpp

llama.cpp is a popular port of Facebook’s LLaMA model in C/C++.

Features

The llama.cpp model supports the following features:

Setup

LocalAI supports llama.cpp models out of the box. You can use the llama.cpp model in the same way as any other model.

Manual setup

It is sufficient to copy the ggml or gguf model files in the models folder. You can refer to the model in the model parameter in the API calls.

You can optionally create an associated YAML model config file to tune the model’s parameters or apply a template to the prompt.

Prompt templates are useful for models that are fine-tuned towards a specific prompt.

Automatic setup

LocalAI supports model galleries which are indexes of models. For instance, the huggingface gallery contains a large curated index of models from the huggingface model hub for ggml or gguf models.

For instance, if you have the galleries enabled and LocalAI already running, you can just start chatting with models in huggingface by running:

  curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
     "model": "TheBloke/WizardLM-13B-V1.2-GGML/wizardlm-13b-v1.2.ggmlv3.q2_K.bin",
     "messages": [{"role": "user", "content": "Say this is a test!"}],
     "temperature": 0.1
   }'

LocalAI will automatically download and configure the model in the model directory.

Models can be also preloaded or downloaded on demand. To learn about model galleries, check out the model gallery documentation.

YAML configuration

To use the llama.cpp backend, specify llama as the backend in the YAML file:

  name: llama
backend: llama
parameters:
  # Relative to the models path
  model: file.gguf.bin

In the example above we specify llama as the backend to restrict loading gguf models only.

For instance, to use the llama-ggml backend for ggml models:

  name: llama
backend: llama-ggml
parameters:
  # Relative to the models path
  model: file.ggml.bin

Reference

exllama/2

Exllama is a “A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights”. Both exllama and exllama2 are supported.

Model setup

Download the model as a folder inside the model directory and create a YAML file specifying the exllama backend. For instance with the TheBloke/WizardLM-7B-uncensored-GPTQ model:

  $ git lfs install
$ cd models && git clone https://huggingface.co/TheBloke/WizardLM-7B-uncensored-GPTQ
$ ls models/                                                                 
.keep                        WizardLM-7B-uncensored-GPTQ/ exllama.yaml
$ cat models/exllama.yaml                                                     
name: exllama
parameters:
  model: WizardLM-7B-uncensored-GPTQ
backend: exllama
# Note: you can also specify "exllama2" if it's an exllama2 model here
# ...

Test with:

  curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{                                                                                                         
   "model": "exllama",
   "messages": [{"role": "user", "content": "How are you?"}],
   "temperature": 0.1
 }'

vLLM

vLLM is a fast and easy-to-use library for LLM inference.

LocalAI has a built-in integration with vLLM, and it can be used to run models. You can check out vllm performance here.

Setup

Create a YAML file for the model you want to use with vllm.

To setup a model, you need to just specify the model name in the YAML config file:

  name: vllm
backend: vllm
parameters:
    model: "facebook/opt-125m"

# Uncomment to specify a quantization method (optional)
# quantization: "awq"
# Uncomment to limit the GPU memory utilization (vLLM default is 0.9 for 90%)
# gpu_memory_utilization: 0.5
# Uncomment to trust remote code from huggingface
# trust_remote_code: true
# Uncomment to enable eager execution
# enforce_eager: true
# Uncomment to specify the size of the CPU swap space per GPU (in GiB)
# swap_space: 2
# Uncomment to specify the maximum length of a sequence (including prompt and output)
# max_model_len: 32768
# Uncomment and specify the number of Tensor divisions.
# Allows you to partition and run large models. Performance gains are limited.
# https://github.com/vllm-project/vllm/issues/1435
# tensor_parallel_size: 2

The backend will automatically download the required files in order to run the model.

Usage

Use the completions endpoint by specifying the vllm backend:

  curl http://localhost:8080/v1/completions -H "Content-Type: application/json" -d '{   
   "model": "vllm",
   "prompt": "Hello, my name is",
   "temperature": 0.1, "top_p": 0.1
 }'

Transformers

Transformers is a State-of-the-art Machine Learning library for PyTorch, TensorFlow, and JAX.

LocalAI has a built-in integration with Transformers, and it can be used to run models.

This is an extra backend - in the container images (the extra images already contains python dependencies for Transformers) is already available and there is nothing to do for the setup.

Setup

Create a YAML file for the model you want to use with transformers.

To setup a model, you need to just specify the model name in the YAML config file:

  name: transformers
backend: transformers
parameters:
    model: "facebook/opt-125m"
type: AutoModelForCausalLM
quantization: bnb_4bit # One of: bnb_8bit, bnb_4bit, xpu_4bit (optional)

The backend will automatically download the required files in order to run the model.

Parameters

Type
Type Description
AutoModelForCausalLM AutoModelForCausalLM is a model that can be used to generate sequences.
OVModelForCausalLM for OpenVINO models
N/A Defaults to AutoModel
Quantization
Quantization Description
bnb_8bit 8-bit quantization
bnb_4bit 4-bit quantization
xpu_4bit 4-bit quantization for Intel XPUs

Usage

Use the completions endpoint by specifying the transformers model:

  curl http://localhost:8080/v1/completions -H "Content-Type: application/json" -d '{   
   "model": "transformers",
   "prompt": "Hello, my name is",
   "temperature": 0.1, "top_p": 0.1
 }'

Examples

OpenVINO

A model configuration file for openvion and starling model:

  name: starling-openvino
backend: transformers
parameters:
  model: fakezeta/Starling-LM-7B-beta-openvino-int8
context_size: 8192
threads: 6
f16: true
type: OVModelForCausalLM
stopwords:
- <|end_of_turn|>
- <|endoftext|>
prompt_cache_path: "cache"
prompt_cache_all: true
template:
  chat_message: |
    {{if eq .RoleName "system"}}{{.Content}}<|end_of_turn|>{{end}}{{if eq .RoleName "assistant"}}<|end_of_turn|>GPT4 Correct Assistant: {{.Content}}<|end_of_turn|>{{end}}{{if eq .RoleName "user"}}GPT4 Correct User: {{.Content}}{{end}}

  chat: |
    {{.Input}}<|end_of_turn|>GPT4 Correct Assistant:

  completion: |
    {{.Input}}
Edit this page

Last updated 22 Apr 2024, 23:37 +0900 . history