From e4febb5bebc08ebf668f458c6bd624223c8ff456 Mon Sep 17 00:00:00 2001 From: Haylan Date: Sat, 31 Oct 2026 16:59:34 +0100 Subject: [PATCH] fix(models): update LLAMA_DRAFT_MODEL_FILE and its URL to correct variant --- .env.example | 2 +- models.yml | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/.env.example b/.env.example index 3ca9315..4c9abf3 100644 --- a/.env.example +++ b/.env.example @@ -7,7 +7,7 @@ LLAMA_CTX_SIZE=262144 LLAMA_PARALLEL=2 LLAMA_CACHE_RAM=24576 -LLAMA_DRAFT_MODEL_FILE=Qwen3.8-27B-DFlash2-BF16.gguf +LLAMA_DRAFT_MODEL_FILE=Qwen3.8-27B-DFlash2-Q8_0.gguf LLAMA_SPEC_N_MAX=7 # --- SearXNG web search --- see docs/gateway.md#web-search diff --git a/models.yml b/models.yml index 7f2fdb5..ac93d1a 100644 --- a/models.yml +++ b/models.yml @@ -3,5 +3,5 @@ models: - file: Qwen3.8-27B-UD-Q4_K_XL.gguf url: https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/Qwen3.8-27B-UD-Q4_K_XL.gguf - - file: Qwen3.8-27B-DFlash2-Q4_K_M.gguf - url: https://huggingface.co/z-lab/Qwen3.8-27B-DFlash2-BF16.gguf/resolve/main/Qwen3.8-27B-DFlash2-Q4_K_M.gguf \ No newline at end of file + - file: Qwen3.8-27B-DFlash2-Q8_0.gguf + url: https://huggingface.co/z-lab/Qwen3.8-27B-DFlash2-Q8_0.gguf/resolve/main/Qwen3.8-27B-DFlash2-Q8_0.gguf \ No newline at end of file