From 79315d32dbd8f7c9438a6969994020c6e5d6963c Mon Sep 17 00:00:00 2001 From: Lumpiasty Date: Mon, 16 Mar 2026 18:19:28 +0100 Subject: [PATCH] add GLM-4.7-Flash model --- apps/llama/configs/config.yaml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/apps/llama/configs/config.yaml b/apps/llama/configs/config.yaml index e3b83bd..9134170 100644 --- a/apps/llama/configs/config.yaml +++ b/apps/llama/configs/config.yaml @@ -10,6 +10,7 @@ macros: qwen35_35b_args: "--temp 1.0 --min-p 0.00 --top-p 0.95 --top-k 20 -ctk q4_0 -ctv q4_0" qwen35_35b_heretic_mmproj: "--mmproj-url https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF/resolve/main/mmproj-F16.gguf --mmproj /root/.cache/llama.cpp/unsloth_Qwen3.5-35B-A3B-GGUF_mmproj-F16.gguf" qwen35_4b_heretic_mmproj: "--mmproj-url https://huggingface.co/unsloth/Qwen3.5-4B-GGUF/resolve/main/mmproj-F16.gguf --mmproj /root/.cache/llama.cpp/unsloth_Qwen3.5-4B-GGUF_mmproj-F16.gguf" + glm47_flash_args: "--temp 0.7 --top-p 1.0 --min-p 0.01 --repeat-penalty 1.0" thinking_on: "--chat-template-kwargs '{\"enable_thinking\": true}'" thinking_off: "--chat-template-kwargs '{\"enable_thinking\": false}'" @@ -226,3 +227,10 @@ models: ${qwen35_sampling} ${common_args} ${thinking_off} + + "GLM-4.7-Flash-GGUF:Q4_K_M": + cmd: | + /app/llama-server + -hf unsloth/GLM-4.7-Flash-GGUF:Q4_K_M + ${glm47_flash_args} + ${common_args}