File size: 1,354 Bytes
bf6b252
1abfb85
 
2c3faec
5018def
2c3faec
f403218
5a92f8f
dc76031
8792ba0
5a92f8f
ba4219c
 
278d687
f58f430
 
e3b3055
52f8103
8523901
985b52d
a202573
d9fcf2b
52f8103
ed8410f
2ff33d5
e10025f
 
5018def
d9fcf2b
8792ba0
2f92469
8792ba0
 
 
 
2f92469
8e15e08
2f92469
8e15e08
40ea0af
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
#!/bin/bash
set -e

# ==========================
# 工作目錄設定
# ==========================
export WORK="/home/user/app"
SERVER_BIN="$WORK/llama-server"

cd "$WORK"
unzip llama_cpp_avx512_17565.zip
echo "PWD"
pwd

#wget https://huggingface.co/unsloth/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B-Q5_K_M.gguf
#wget https://huggingface.co/unsloth/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B-Q2_K.gguf
#wget https://huggingface.co/unsloth/LFM2-8B-A1B-GGUF/resolve/main/LFM2-8B-A1B-UD-Q4_K_XL.gguf
#wget https://huggingface.co/unsloth/ERNIE-4.5-21B-A3B-Thinking-GGUF/resolve/main/ERNIE-4.5-21B-A3B-Thinking-UD-IQ2_M.gguf
#wget https://huggingface.co/unsloth/LFM2.5-1.2B-Instruct-GGUF/resolve/main/LFM2.5-1.2B-Instruct-Q4_0.gguf
#wget https://huggingface.co/unsloth/gpt-oss-20b-GGUF/resolve/main/gpt-oss-20b-Q4_0.gguf
#wget https://huggingface.co/inclusionAI/Ling-mini-2.0-GGUF/resolve/main/Ling-mini-2.0-Q4_K_M.gguf
wget https://huggingface.co/unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF/resolve/main/Qwen3-30B-A3B-Instruct-2507-UD-IQ1_S.gguf

echo "ls -l"
ls -l

#    --models-dir $WORK \
$SERVER_BIN \
    --model Qwen3-30B-A3B-Instruct-2507-UD-IQ1_S.gguf \
    --threads 2 \
    --ctx-size 4096 \
    --mlock \
    --temp 1.1 \
    --top-p 0.95 \
    --jinja \
    --chat-template ""  \
    --host 0.0.0.0 \
    --port 7860 \
    --models-max 1 \
    --verbose