haylan/LLM-Server
1
0 Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity

chore(models): update LLAMA_DRAFT_MODEL_FILE and its URL to use BF16 variant

Browse Source
This commit is contained in:
haylan committed 2026-10-31 16:54:15 +01:00
1 parent 8144286946
commit d5712d5fd4
2 files changed
+2 -2
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.env.example
+1 -1
View File
@@ -7,7 +7,7 @@ LLAMA_CTX_SIZE=262144
LLAMA_PARALLEL=2 LLAMA_PARALLEL=2
LLAMA_CACHE_RAM=24576 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 LLAMA_SPEC_N_MAX=7
# --- SearXNG web search --- see docs/gateway.md#web-search # --- SearXNG web search --- see docs/gateway.md#web-search
models.yml
+1 -1
View File
@@ -4,4 +4,4 @@ models:
- file: Qwen3.8-27B-UD-Q4_K_XL.gguf - 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 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 - 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