mirror of
https://github.com/mudler/LocalAI.git
synced 2024-06-07 19:40:48 +00:00
95 lines
2.9 KiB
YAML
95 lines
2.9 KiB
YAML
|
replicaCount: 1
|
||
|
|
|
||
|
|
deployment:
|
||
|
|
# https://quay.io/repository/go-skynet/local-ai?tab=tags
|
||
|
|
image: quay.io/go-skynet/local-ai:latest
|
||
|
|
env:
|
||
|
|
threads: 4
|
||
|
|
debug: "true"
|
||
|
|
context_size: 512
|
||
|
|
preload_models: '[{ "url": "github:go-skynet/model-gallery/wizard.yaml", "name": "gpt-3.5-turbo", "overrides": { "parameters": { "model": "WizardLM-7B-uncensored.ggmlv3.q5_1" }},"files": [ { "uri": "https://huggingface.co//WizardLM-7B-uncensored-GGML/resolve/main/WizardLM-7B-uncensored.ggmlv3.q5_1.bin", "sha256": "d92a509d83a8ea5e08ba4c2dbaf08f29015932dc2accd627ce0665ac72c2bb2b", "filename": "WizardLM-7B-uncensored.ggmlv3.q5_1" }]}]'
|
||
|
|
modelsPath: "/models"
|
||
|
|
|
||
|
|
resources:
|
||
|
|
{}
|
||
|
|
# We usually recommend not to specify default resources and to leave this as a conscious
|
||
|
|
# choice for the user. This also increases chances charts run on environments with little
|
||
|
|
# resources, such as Minikube. If you do want to specify resources, uncomment the following
|
||
|
|
# lines, adjust them as necessary, and remove the curly braces after 'resources:'.
|
||
|
|
# limits:
|
||
|
|
# cpu: 100m
|
||
|
|
# memory: 128Mi
|
||
|
|
# requests:
|
||
|
|
# cpu: 100m
|
||
|
|
# memory: 128Mi
|
||
|
|
|
||
|
|
# Prompt templates to include
|
||
|
|
# Note: the keys of this map will be the names of the prompt template files
|
||
|
|
promptTemplates:
|
||
|
|
{}
|
||
|
|
# ggml-gpt4all-j.tmpl: |
|
||
|
|
# The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
|
||
|
|
# ### Prompt:
|
||
|
|
# {{.Input}}
|
||
|
|
# ### Response:
|
||
|
|
|
||
|
|
# Models to download at runtime
|
||
|
|
models:
|
||
|
|
# Whether to force download models even if they already exist
|
||
|
|
forceDownload: false
|
||
|
|
|
||
|
|
# The list of URLs to download models from
|
||
|
|
# Note: the name of the file will be the name of the loaded model
|
||
|
|
list:
|
||
|
|
#- url: "https://gpt4all.io/models/ggml-gpt4all-j.bin"
|
||
|
|
# basicAuth: base64EncodedCredentials
|
||
|
|
|
||
|
|
# Persistent storage for models and prompt templates.
|
||
|
|
# PVC and HostPath are mutually exclusive. If both are enabled,
|
||
|
|
# PVC configuration takes precedence. If neither are enabled, ephemeral
|
||
|
|
# storage is used.
|
||
|
|
persistence:
|
||
|
|
pvc:
|
||
|
|
enabled: false
|
||
|
|
size: 6Gi
|
||
|
|
accessModes:
|
||
|
|
- ReadWriteOnce
|
||
|
|
|
||
|
|
annotations: {}
|
||
|
|
|
||
|
|
# Optional
|
||
|
|
storageClass: ~
|
||
|
|
|
||
|
|
hostPath:
|
||
|
|
enabled: false
|
||
|
|
path: "/models"
|
||
|
|
|
||
|
|
service:
|
||
|
|
type: ClusterIP
|
||
|
|
port: 8080
|
||
|
|
annotations: {}
|
||
|
|
# If using an AWS load balancer, you'll need to override the default 60s load balancer idle timeout
|
||
|
|
# service.beta.kubernetes.io/aws-load-balancer-connection-idle-timeout: "1200"
|
||
|
|
|
||
|
|
ingress:
|
||
|
|
enabled: false
|
||
|
|
className: ""
|
||
|
|
annotations:
|
||
|
|
{}
|
||
|
|
# kubernetes.io/ingress.class: nginx
|
||
|
|
# kubernetes.io/tls-acme: "true"
|
||
|
|
hosts:
|
||
|
|
- host: chart-example.local
|
||
|
|
paths:
|
||
|
|
- path: /
|
||
|
|
pathType: ImplementationSpecific
|
||
|
|
tls: []
|
||
|
|
# - secretName: chart-example-tls
|
||
|
|
# hosts:
|
||
|
|
# - chart-example.local
|
||
|
|
|
||
|
|
nodeSelector: {}
|
||
|
|
|
||
|
|
tolerations: []
|
||
|
|
|
||
|
|
affinity: {}
|