Closed renovate[bot] closed 1 month ago
--- kubernetes/ml/prod Kustomization: flux-system/ml HelmRelease: llama/llama-openblas
+++ kubernetes/ml/prod Kustomization: flux-system/ml HelmRelease: llama/llama-openblas
@@ -45,13 +45,13 @@
value: /data/models
- name: MODEL_URLS
value: https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf,https://huggingface.co/chanwit/flux-7b-v0.1-gguf/resolve/main/flux-7b-v0.1-Q4_K_M.gguf,https://huggingface.co/meetkai/functionary-7b-v1.4-GGUF/resolve/main/functionary-7b-v1.4.q4_0.gguf,https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-GGUF/resolve/main/deepseek-coder-6.7b-instruct.Q4_K_M.gguf
image:
pullPolicy: IfNotPresent
repository: ghcr.io/allenporter/llama-cpp-server-model-fetch
- tag: v2.16.0
+ tag: v2.17.0
strategy: Recreate
ingress:
main:
annotations:
cert-manager.io/cluster-issuer: letsencrypt
enabled: true
--- HelmRelease: llama/llama-openblas Deployment: llama/llama-openblas
+++ HelmRelease: llama/llama-openblas Deployment: llama/llama-openblas
@@ -35,13 +35,13 @@
initContainers:
- env:
- name: MODEL_DIR
value: /data/models
- name: MODEL_URLS
value: https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf,https://huggingface.co/chanwit/flux-7b-v0.1-gguf/resolve/main/flux-7b-v0.1-Q4_K_M.gguf,https://huggingface.co/meetkai/functionary-7b-v1.4-GGUF/resolve/main/functionary-7b-v1.4.q4_0.gguf,https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-GGUF/resolve/main/deepseek-coder-6.7b-instruct.Q4_K_M.gguf
- image: ghcr.io/allenporter/llama-cpp-server-model-fetch:v2.16.0
+ image: ghcr.io/allenporter/llama-cpp-server-model-fetch:v2.17.0
imagePullPolicy: IfNotPresent
name: download-model
volumeMounts:
- mountPath: /config/model-config.json
name: config
readOnly: true
This PR contains the following updates:
v2.16.0
->v2.17.0
Release Notes
allenporter/llama-cpp-server (ghcr.io/allenporter/llama-cpp-server-model-fetch)
### [`v2.17.0`](https://togithub.com/allenporter/llama-cpp-server/releases/tag/v2.17.0) [Compare Source](https://togithub.com/allenporter/llama-cpp-server/compare/v2.16.0...v2.17.0) ### Changes - Adds transformers dependency needed by functionary **Full Changelog**: https://github.com/allenporter/llama-cpp-server/compare/v2.16.0...v2.17.0Configuration
📅 Schedule: Branch creation - "every weekend" in timezone America/Los_Angeles, Automerge - At any time (no schedule defined).
🚦 Automerge: Enabled.
â™» Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.
🔕 Ignore: Close this PR and you won't be reminded about this update again.
This PR has been generated by Mend Renovate. View repository job log here.