admin/momentry_core
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: Phase 1 completion report + LLM reasoning off fix

Browse Source
This commit is contained in:
Accusys
2026-05-09 22:03:34 +08:00
parent e7f311e7b8
commit d043b6adae
2 changed files with 112 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/start_momentry.sh
View File

@@ -85,7 +85,7 @@ if curl -s -o /dev/null -w "%{http_code}" --connect-timeout 5 http://localhost:8
else
LLM_BIN="/Users/accusys/llama/bin/llama-server"
LLM_MODEL="/Users/accusys/models/google_gemma-4-26B-A4B-it-Q5_K_M.gguf"
nohup "$LLM_BIN" -m "$LLM_MODEL" --host 0.0.0.0 --port 8082 -ngl 99 -c 16384 --temp 0.1 --mlock > "$LOG_DIR/llama_server.log" 2>&1 &
nohup "$LLM_BIN" -m "$LLM_MODEL" --host 0.0.0.0 --port 8082 -ngl 99 -c 16384 --temp 0.1 --mlock --reasoning off > "$LOG_DIR/llama_server.log" 2>&1 &
echo -e " ${YELLOW}⏳ loading model (~30s)...${NC}"
for i in $(seq 1 30); do
sleep 2