From ec1153d3d6d4f4bb9cdf7a6f2fe8e5c63733e389 Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Wed, 29 Apr 2026 16:59:42 -0700 Subject: [PATCH] docs: delete stale docs/pfi/model-list.md (1 file) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Self-reported "Synchronized with llama-swap config.yaml on 2025-07-18" — 9 months stale. Canonical model truth is stacks/llama-swap/conf/config.yaml; the static snapshot was guaranteed to drift. No historical value (not an ADR, post-mortem, or migration runbook). Found via /tend-docs. --- docs/pfi/model-list.md | 81 ------------------------------------------ 1 file changed, 81 deletions(-) delete mode 100644 docs/pfi/model-list.md diff --git a/docs/pfi/model-list.md b/docs/pfi/model-list.md deleted file mode 100644 index 5bd5a56..0000000 --- a/docs/pfi/model-list.md +++ /dev/null @@ -1,81 +0,0 @@ -# PFI-ANA Model Inventory -# Generated from: find /models -maxdepth 3 -name "*.gguf" | sort -# Synchronized with llama-swap config.yaml on 2025-07-18 -# -# Status Key: -# [ACTIVE] = configured in llama-swap -# [PENDING] = on disk, not yet in config (or still downloading) -# [REMOVED] = was in old config, not on disk -# -# ============================================================================ -# KB Optimization Pass (2025-07-18): -# - Qwen 3.5: added presence_penalty, thinking mode enable_thinking -# - Qwen3-Coder-Next: temp 0.3→1.0, top-p 0.85→0.95, top-k 20→40, min-p 0→0.01 -# - Gemma 4: added repeat_penalty 1.0, thinking mode enable_thinking -# - Nemotron: already applied in prior pass (--special, min-p 0.01, seed 3407) -# ============================================================================ - -[ACTIVE] ./ggml-org_Qwen3-Reranker-0.6B-Q8_0-GGUF/qwen3-reranker-0.6b-q8_0.gguf - -[ACTIVE] ./unsloth_Qwen3.5-122B-A10B-GGUF/UD-Q4_K_XL/Qwen3.5-122B-A10B-UD-Q4_K_XL-00001-of-00003.gguf -[ACTIVE] ./unsloth_Qwen3.5-122B-A10B-GGUF/UD-Q4_K_XL/Qwen3.5-122B-A10B-UD-Q4_K_XL-00002-of-00003.gguf -[ACTIVE] ./unsloth_Qwen3.5-122B-A10B-GGUF/UD-Q4_K_XL/Qwen3.5-122B-A10B-UD-Q4_K_XL-00003-of-00003.gguf - -[ACTIVE] ./ibm-granite_granite-4.0-micro-GGUF/granite-4.0-micro-Q4_K_M.gguf - -[ACTIVE] ./unsloth_GLM-4.7-Flash-GGUF/GLM-4.7-Flash-UD-Q4_K_XL.gguf - -[ACTIVE] ./jinaai_jina-reranker-v3-GGUF/jina-reranker-v3-Q8_0.gguf - -[ACTIVE] ./unsloth_NVIDIA-Nemotron-3-Super-120B-A12B-GGUF/UD-Q4_K_XL/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_XL-00001-of-00003.gguf -[ACTIVE] ./unsloth_NVIDIA-Nemotron-3-Super-120B-A12B-GGUF/UD-Q4_K_XL/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_XL-00002-of-00003.gguf -[ACTIVE] ./unsloth_NVIDIA-Nemotron-3-Super-120B-A12B-GGUF/UD-Q4_K_XL/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_XL-00003-of-00003.gguf - -[ACTIVE] ./bartowski_TheDrummer_Skyfall-31B-v4-GGUF/TheDrummer_Skyfall-31B-v4-Q6_K_L.gguf - -[ACTIVE] ./RP/BeaverAI_Skyfall-R1-31B-v4a-GGUF/Skyfall-R1-31B-v4a-Q6_K.gguf - -[ACTIVE] ./RP/bartowski_TheDrummer_GLM-Steam-106B-A12B-v1-GGUF/TheDrummer_GLM-Steam-106B-A12B-v1-Q4_K_M-00001-of-00002.gguf -[ACTIVE] ./RP/bartowski_TheDrummer_GLM-Steam-106B-A12B-v1-GGUF/TheDrummer_GLM-Steam-106B-A12B-v1-Q4_K_M-00002-of-00002.gguf - -[ACTIVE] ./unsloth_Qwen3.5-9B-GGUF/Qwen3.5-9B-UD-Q4_K_XL.gguf - -[ACTIVE] ./unsloth_granite-4.0-h-small-GGUF/granite-4.0-h-small-Q4_K_M.gguf - -[ACTIVE] ./unsloth_Kimi-K2-Instruct-0905-GGUF/UD-Q2_K_XL/Kimi-K2-Instruct-0905-UD-Q2_K_XL-00001-of-00008.gguf -[ACTIVE] ./unsloth_Kimi-K2-Instruct-0905-GGUF/UD-Q2_K_XL/Kimi-K2-Instruct-0905-UD-Q2_K_XL-00002-of-00008.gguf -[ACTIVE] ./unsloth_Kimi-K2-Instruct-0905-GGUF/UD-Q2_K_XL/Kimi-K2-Instruct-0905-UD-Q2_K_XL-00003-of-00008.gguf -[ACTIVE] ./unsloth_Kimi-K2-Instruct-0905-GGUF/UD-Q2_K_XL/Kimi-K2-Instruct-0905-UD-Q2_K_XL-00004-of-00008.gguf -[ACTIVE] ./unsloth_Kimi-K2-Instruct-0905-GGUF/UD-Q2_K_XL/Kimi-K2-Instruct-0905-UD-Q2_K_XL-00005-of-00008.gguf -[ACTIVE] ./unsloth_Kimi-K2-Instruct-0905-GGUF/UD-Q2_K_XL/Kimi-K2-Instruct-0905-UD-Q2_K_XL-00006-of-00008.gguf -[ACTIVE] ./unsloth_Kimi-K2-Instruct-0905-GGUF/UD-Q2_K_XL/Kimi-K2-Instruct-0905-UD-Q2_K_XL-00007-of-00008.gguf -[ACTIVE] ./unsloth_Kimi-K2-Instruct-0905-GGUF/UD-Q2_K_XL/Kimi-K2-Instruct-0905-UD-Q2_K_XL-00008-of-00008.gguf - -[PENDING] ./unsloth_Qwen3-Coder-Next-GGUF/Qwen3-Coder-Next-UD-Q4_K_XL.gguf - NOTE: Download may be incomplete (has .incomplete files). Config entry ready. - -[ACTIVE] ./unsloth_Nemotron-3-Nano-30B-A3B-GGUF/Nemotron-3-Nano-30B-A3B-UD-Q4_K_XL.gguf - -[ACTIVE] ./unsloth_gemma-4-26B-A4B-it-GGUF/gemma-4-26B-A4B-it-UD-Q4_K_XL.gguf - -[ACTIVE] ./unsloth_Qwen3.5-35B-A3B-GGUF/Qwen3.5-35B-A3B-UD-Q4_K_XL.gguf - -[ACTIVE] ./Qwen_Qwen3-Embedding-0.6B-GGUF/Qwen3-Embedding-0.6B-Q8_0.gguf - -[ACTIVE] ./unsloth_gemma-4-31B-it-GGUF/gemma-4-31B-it-UD-Q4_K_XL.gguf - -[ACTIVE] ./ggml-org_embeddinggemma-300M-GGUF/embeddinggemma-300M-Q8_0.gguf - -# ============================================================================ -# MODELS REMOVED FROM CONFIG (not on disk or superseded): -# ============================================================================ -# [REMOVED] qwen3-4b — Qwen3-4B-Instruct-2507-Q6_K (not on disk) -# [REMOVED] glm4.5-air — GLM-4.5-Air-Q4_K_M (not on disk, superseded by glm4.7-flash) -# [REMOVED] qwen3-coder-30b — Qwen3-Coder-30B-A3B (not on disk, superseded by qwen3-coder-next) -# [REMOVED] bge-reranker-v2-m3 — Replaced by qwen3-reranker-0.6B -# [FIXED] glm-steam-106b — Path fixed: was missing RP/ prefix -# ============================================================================ -# STILL DOWNLOADING (not yet configured): -# ============================================================================ -# [PENDING] Hermes-4-14B — Multiple quant downloads in progress (.incomplete files) -# ============================================================================