simplify readme

examples/inference/api_demo.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0 API_PORT=8000 python src/api_demo.py \
+    --model_name_or_path meta-llama/Llama-2-7b-hf \
+    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
+    --template default \
+    --finetuning_type lora

examples/inference/cli_demo.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0 python src/cli_demo.py \
+    --model_name_or_path meta-llama/Llama-2-7b-hf \
+    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
+    --template default \
+    --finetuning_type lora

examples/inference/evaluate.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0 python src/evaluate.py \
+    --model_name_or_path meta-llama/Llama-2-7b-hf \
+    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
+    --template vanilla \
+    --finetuning_type lora \
+    --task mmlu \
+    --split test \
+    --lang en \
+    --n_shot 5 \
+    --batch_size 4

examples/inference/web_demo.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0 python src/web_demo.py \
+    --model_name_or_path meta-llama/Llama-2-7b-hf \
+    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
+    --template default \
+    --finetuning_type lora