From d5712d5fd4263f9950b8ecb47fb6a480d95a3c65 Mon Sep 17 00:00:00 2001 From: Haylan Date: Sat, 31 Oct 2026 16:54:15 +0100 Subject: [PATCH] chore(models): update LLAMA_DRAFT_MODEL_FILE and its URL to use BF16 variant --- .env.example | 2 +- models.yml | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/.env.example b/.env.example index 45e09ee..3ca9315 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-Q4_K_M.gguf +LLAMA_DRAFT_MODEL_FILE=Qwen3.8-27B-DFlash2-BF16.gguf LLAMA_SPEC_N_MAX=7 # --- SearXNG web search --- see docs/gateway.md#web-search diff --git a/models.yml b/models.yml index c4df725..7f2fdb5 100644 --- a/models.yml +++ b/models.yml @@ -4,4 +4,4 @@ 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-GGUF/resolve/main/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