Upload RUN_SERVER.txt

RUN_SERVER.txt

@@ -0,0 +1,29 @@
+QUANTIZAÇÃO -------------------------------------------------------------------------------------------
+
+-------------------------------------------------------------------------------------------------------------
+./llama.cpp/build/bin/llama-quantize ./GGUFS/granite-3.3-8b-instruct-f16.gguf ./GGUFS/ΩFFΣLLIα_granite-3.3-8b-instruct-Q4_K_M.gguf Q4_K_M
+
+
+-------------------------------------------------------------------------------------------------------------
+
+
+/home/userk21/llama.cpp/build/bin/llama-server \
+-m /home/userk21/GGUFS/ΩFFΣLLIα_LFM2-8B-A1B-Q6_K.gguf \
+--ctx-size 120000
+--threads $(nproc) \
+--ignore-eos \
+--n-predict -1
+--flash-attn on \
+--port 3301 \
+--host 0.0.0.0
+
+------------------------------------------------------------------------------------------------------------
+
+/home/userk21/llama.cpp/build/bin/llama-server \
+-m /home/userk21/GGUFS/ΩFFΣLLIα_granite-3.3-8b-instruct-Q4_K_M.gguf \
+--threads $(nproc) \
+--ignore-eos \
+--n-predict -1
+--flash-attn on \
+--port 3301 \
+--host 0.0.0.0