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)
This commit is contained in:
Frank committed 2026-08-30 02:26:49 -07:00
1 parent 3066d810ee
commit aa9c1d065a
4 files changed
+29 -20

No files matched your search

+1 -1
View File
@@ -1,5 +1,5 @@
[Unit]
Description=FreeToken Qwen3.6-35B-A3B-FP8 qwen3_5_moe hybrid MoE (dankserver, frank-default-small)
Description=FreeToken Huihui-Qwen3.6-35B-A3B-abliterated-FP8 qwen3_5_moe hybrid MoE (dankserver, frank-default-small)
After=network-online.target
Wants=network-online.target