- 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)
17 lines
463 B
Desktop File
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
|