tomasz-syn-grzegorza
359afb3a59
Infrastructure configs for GMKtec K11 (Docker, vLLM, LocalAI, ComfyUI, control-plane, gpu-fan agent, Server UI with CLI/file explorer/GPU fan curve). Co-authored-by: Cursor <cursoragent@cursor.com>
33 lines
836 B
Plaintext
33 lines
836 B
Plaintext
# Szablon: Gemma 4 12B Q4_0 z kwantyzowanym KV cache (q8_0)
|
|
#
|
|
# Zastosowanie na serwerze:
|
|
# ./scripts/apply-kv-profile.sh gemma-4-12b-it-qat-q4_0
|
|
# lub skopiuj sekcję parameters do /data/apps/localai/models/<nazwa>.yaml
|
|
#
|
|
# Dokumentacja: coding-agent/KV-CACHE.md
|
|
|
|
name: gemma-4-12b-it-qat-q4_0
|
|
backend: llama-cpp
|
|
mmproj: llama-cpp/mmproj/gemma-4-12B-it-qat-q4_0-gguf/mmproj-gemma-4-12b-it-qat-q4_0.gguf
|
|
known_usecases:
|
|
- chat
|
|
options:
|
|
- use_jinja:true
|
|
parameters:
|
|
model: llama-cpp/models/gemma-4-12B-it-qat-q4_0-gguf/gemma-4-12b-it-qat-q4_0.gguf
|
|
cache_type_k: q8_0
|
|
cache_type_v: q8_0
|
|
flash_attention: true
|
|
context_size: 8192
|
|
temperature: 1
|
|
top_p: 0.95
|
|
top_k: 64
|
|
repeat_penalty: 1
|
|
min_p: 0
|
|
template:
|
|
use_tokenizer_template: true
|
|
function:
|
|
automatic_tool_parsing_fallback: true
|
|
grammar:
|
|
disable: true
|