#!/bin/bash

# 定义变量
MODEL_OUTPUT_PATH="./bundle"
QUANTIZATION="q0f16"

MODEL_PATH="Llama3.1-8B-Instruct-Tinytron"
MODEL_NAME="Llama3.1-8B-Instruct-Tinytron-MLC"
# 转换权重
mlc_llm convert_weight --device cpu ${MODEL_PATH}/ --quantization ${QUANTIZATION} -o ${MODEL_OUTPUT_PATH}/${MODEL_NAME}/

# 生成配置
mlc_llm gen_config ${MODEL_PATH}  --conv-template llama-3_1 --quantization ${QUANTIZATION} --context-window-size 512 --prefill-chunk-size=16 --max-batch-size=1 -o ${MODEL_OUTPUT_PATH}/${MODEL_NAME}/


# 切换模型
MODEL_PATH="Qwen2-7B-Instruct-Tinytron"
MODEL_NAME="Qwen2-7B-Instruct-Tinytron-MLC"
# 转换权重
mlc_llm convert_weight --device cpu ${MODEL_PATH} --quantization ${QUANTIZATION} -o ${MODEL_OUTPUT_PATH}/${MODEL_NAME}/

# 生成配置
mlc_llm gen_config ${MODEL_PATH}  --conv-template qwen2 --quantization ${QUANTIZATION} --context-window-size 512 --prefill-chunk-size=16 --max-batch-size=1 -o ${MODEL_OUTPUT_PATH}/${MODEL_NAME}/

# 切换模型
MODEL_PATH="Phi-2-Tinytron-preview"
MODEL_NAME="Phi-2-Tinytron-preview-MLC"
# 转换权重
mlc_llm convert_weight --device cpu ${MODEL_PATH} --quantization ${QUANTIZATION} -o ${MODEL_OUTPUT_PATH}/${MODEL_NAME}/

# 生成配置
mlc_llm gen_config ${MODEL_PATH}  --conv-template qwen2 --quantization ${QUANTIZATION} --context-window-size 512 --prefill-chunk-size=16 --max-batch-size=1 -o ${MODEL_OUTPUT_PATH}/${MODEL_NAME}/

MODEL_PATH="Cauchy-3B-preview"
MODEL_NAME="Cauchy-3B-preview-MLC"
# 转换权重
mlc_llm convert_weight --model-type cauchy  --device cpu ${MODEL_PATH} --quantization ${QUANTIZATION} -o ${MODEL_OUTPUT_PATH}/${MODEL_NAME}/

# 生成配置
mlc_llm gen_config ${MODEL_PATH} --model-type cauchy --conv-template qwen2 --quantization ${QUANTIZATION} --context-window-size 512 --prefill-chunk-size=16 --max-batch-size=1 -o ${MODEL_OUTPUT_PATH}/${MODEL_NAME}/