jimmychen/NormalCommands
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

添加deepseek-rs分析指令

Browse Source
This commit is contained in:
jimmychen
2026-04-04 22:27:11 -04:00
parent cd20be9f21
commit ae152ccc4e
1 changed files with 7 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
llama-cpp.md
View File

@@ -11,3 +11,10 @@ No thinking: --chat-template-kwargs "{\"enable_thinking\": false}"
./llama-server --model /home/jimmy/NVME/model/gemma-4-31B-it-UD-Q4_K_XL.gguf --mmproj /home/jimmy/NVME/model/gemma4-31b-mmproj-BF16.gguf --temp 1.0 --top-p 0.95 --top-k 64 --alias "gemma-4-31B" --host 0.0.0.0 --port 11434 --kv-unified --cache-type-k q8_0 --cache-type-v q8_0 --flash-attn on --fit on --ctx-size 100000 --jinja --no-mmap -t 24 -np 4 -ngl 999 --chat-template-kwargs '{"enable_thinking":true}' --n-cpu-moe 5 ./llama-server --model /home/jimmy/NVME/model/gemma-4-31B-it-UD-Q4_K_XL.gguf --mmproj /home/jimmy/NVME/model/gemma4-31b-mmproj-BF16.gguf --temp 1.0 --top-p 0.95 --top-k 64 --alias "gemma-4-31B" --host 0.0.0.0 --port 11434 --kv-unified --cache-type-k q8_0 --cache-type-v q8_0 --flash-attn on --fit on --ctx-size 100000 --jinja --no-mmap -t 24 -np 4 -ngl 999 --chat-template-kwargs '{"enable_thinking":true}' --n-cpu-moe 5
## deepseek-rs
./deepwiki-rs -p ./src --llm-api-base-url http://192.168.2.105:11434 --model-efficient Qwen3.5-35B-A3B --target-language zh --max-parallels 4 --max-tokens 262144 --force-regenerate