Files
abap-llm/train/serve.sh

12 lines
439 B
Bash
Executable File

#!/bin/sh
# Serve the base model (no adapter) with mlx_lm.server. Settings: train/README.md.
# Usage: train/serve.sh [--adapter-path PATH]
cd "$(dirname "$0")/.."
exec train/.venv/bin/mlx_lm.server \
--model "$HOME/models/Qwen3.8-27B-4bit" \
--host 127.0.0.1 --port 8080 \
--temp 0.2 --top-p 0.95 --top-k 20 --min-p 0 \
--max-tokens 32768 \
--chat-template-args '{"enable_thinking": true, "reasoning_effort": "medium"}' \
"$@"