From fe1d834d37e38da1d8d60e2fe09502cba76852ec Mon Sep 17 00:00:00 2001 From: Frank Date: Mon, 17 Aug 2026 23:12:32 -0700 Subject: [PATCH] docs: note 128K context and thinking on for frank-default-small --- docs/ciru-activefpx-promptforge.md | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/docs/ciru-activefpx-promptforge.md b/docs/ciru-activefpx-promptforge.md index 1e82eb7..d9cf285 100644 --- a/docs/ciru-activefpx-promptforge.md +++ b/docs/ciru-activefpx-promptforge.md @@ -131,9 +131,12 @@ Downloaded with the HF token to ### Launch profile (from the model card) -- 64K context, one slot, f16 KV, context checkpoints (32), prompt cache +- 128K context (user request 2026-08-18; model card default is 64K), one + slot, f16 KV (8 GiB at 128K, ~51.5 GiB total used of 64 GiB), context + checkpoints (32), prompt cache - Native MTP draft, depth 4, device ROCm0 -- `--temp 0.7 --top-p 0.95`, reasoning off +- `--temp 0.7 --top-p 0.95`, reasoning on (`--reasoning-format deepseek` + puts `` reasoning in `message.reasoning_content`) - PromptForge env: `PROMPTFORGE_MODE=m2048_fused_tail1476`, `GGML_CUDA_GRAPH_OPT=0`, `LLAMA_MTP_CPU_ARGMAX_FASTPATH=1`