marc
/
Cortex
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Verbessung gemäss ChatGPT

This commit is contained in:
Marc Blatter 2026-07-26 12:22:14 +00:00
parent 32bef0cd87
commit 42fb0e0e99
1 changed files with 8 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
composte-hermes.yml
View File

@ -22,18 +22,13 @@ services:
capabilities: [gpu] capabilities: [gpu]
command: command:
- --model=Qwen/Qwen3-14B-AWQ - --model=Qwen/Qwen3-14B-AWQ
- --port=8005
- --quantization=awq
- --tensor-parallel-size=2 - --tensor-parallel-size=2
- --gpu-memory-utilization=0.82 - --gpu-memory-utilization=0.90
- --max-model-len=65536 - --max-model-len=65536
- --hf-overrides={"rope_scaling":{"rope_type":"yarn","factor":2.0,"original_max_position_embeddings":32768}} - --enable-prefix-caching
- --max-num-seqs=16
- --kv-cache-dtype=fp8
- --served-model-name=qwen3-14b-awq
- --enable-auto-tool-choice - --enable-auto-tool-choice
- --tool-call-parser=hermes - --tool-call-parser=hermes
- --reasoning-parser=deepseek_r1 - --max-num-seqs=4
healthcheck: healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8005/health"] test: ["CMD", "curl", "-f", "http://localhost:8005/health"]
interval: 30s interval: 30s