4 Commits

3 changed files with 5 additions and 5 deletions

View File

@@ -8,8 +8,8 @@ macros:
gemma3_ctx_128k: "--ctx-size 131072"
qwen35_ctx_256k: "--ctx-size 262144"
gemma_sampling: "--prio 2 --temp 1.0 --repeat-penalty 1.0 --min-p 0.00 --top-k 64 --top-p 0.95"
qwen35_sampling: "--temp 0.6 --top-p 0.95 --top-k 20 --min-p 0.00 -ctk q4_0 -ctv q4_0"
qwen35_35b_args: "--temp 1.0 --min-p 0.00 --top-p 0.95 --top-k 20 -ctk q4_0 -ctv q4_0"
qwen35_sampling: "--temp 0.6 --top-p 0.95 --top-k 20 --min-p 0.00 -ctk q8_0 -ctv q8_0"
qwen35_35b_args: "--temp 1.0 --min-p 0.00 --top-p 0.95 --top-k 20 -ctk q8_0 -ctv q8_0"
qwen35_35b_heretic_mmproj: "--mmproj-url https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF/resolve/main/mmproj-F16.gguf --mmproj /root/.cache/llama.cpp/unsloth_Qwen3.5-35B-A3B-GGUF_mmproj-F16.gguf"
qwen35_4b_heretic_mmproj: "--mmproj-url https://huggingface.co/unsloth/Qwen3.5-4B-GGUF/resolve/main/mmproj-F16.gguf --mmproj /root/.cache/llama.cpp/unsloth_Qwen3.5-4B-GGUF_mmproj-F16.gguf"
glm47_flash_args: "--temp 0.7 --top-p 1.0 --min-p 0.01 --repeat-penalty 1.0"
@@ -82,7 +82,7 @@ models:
--top-p 0.95
--top-k 40
--repeat-penalty 1.0
-ctk q4_0 -ctv q4_0
-ctk q8_0 -ctv q8_0
${common_args}
"Qwen3.5-35B-A3B-GGUF:Q4_K_M":

View File

@@ -18,7 +18,7 @@ spec:
spec:
containers:
- name: llama-swap
image: ghcr.io/mostlygeek/llama-swap:v198-vulkan-b8390
image: ghcr.io/mostlygeek/llama-swap:v198-vulkan-b8400
imagePullPolicy: IfNotPresent
command:
- /app/llama-swap

View File

@@ -15,7 +15,7 @@ spec:
- name: renovate
# Update this to the latest available and then enable Renovate on
# the manifest
image: renovate/renovate:43.76.1-full
image: renovate/renovate:43.83.1-full
envFrom:
- secretRef:
name: renovate-gitea-token