Files
serverAppConfigs/scripts/frank-default-large.service
T
Frank aa9c1d065a frank-default-small: swap to batsclamp Huihui-Qwen3.6-35B-A3B-abliterated-FP8 on FreeToken
- same qwen3_5_moe arch and native block-fp8 format (e4m3, 128x128
  weight_block_size, un-fused per-expert layout) as the official
  Qwen FP8 checkpoint: identical FreeToken loader path, pool numbers
  unchanged (2048 MoE slots / 453005 KV tokens / 4 requests)
- checkpoint downloaded to /home/dank/models/huihui-qwen36-35b-a3b-abliterated-fp8
  (26 shards, ~35G); official checkpoint kept for rollback
- ships froggeric fixed Qwen3.6 chat template, read from checkpoint
- also refresh both .service Descriptions (large still said STRIX_LEAN)
2026-08-30 02:26:49 -07:00

17 lines
463 B
Desktop File

[Unit]
Description=ROCmFPX (kingjones30 fork) llama.cpp Qwen3.8-Flash-Next ROCmFP4 STRIX 177B MoE (dankclaw, frank-default-large)
After=network-online.target
Wants=network-online.target
[Service]
Type=simple
User=dank
Group=dank
Environment="FRANK_LARGE_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-default-large.env"
ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-large.sh
Restart=on-failure
RestartSec=10
[Install]
WantedBy=multi-user.target