add examples

examples/lora_single_gpu/README.md

@@ -0,0 +1,5 @@
+Usage:
+
+- `pretrain.sh`
+- `sft.sh` -> `reward.sh` -> `ppo.sh`
+- `sft.sh` -> `dpo.sh` -> `predict.sh`

examples/merge_lora/README.md

@@ -0,0 +1,3 @@
+Usage:
+
+- `merge.sh` -> `quantize.sh`

examples/merge_lora/merge.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+python ../../src/export_model.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 \
+    --export_dir ../../models/llama2-7b-sft \
+    --export_size 2 \
+    --export_legacy_format False

examples/merge_lora/quantize.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+python ../../src/export_model.py \
+    --model_name_or_path ../../models/llama2-7b-sft \
+    --template default \
+    --export_dir ../../models/llama2-7b-sft-int4 \
+    --export_quantization_bit 4 \
+    --export_quantization_dataset ../../data/c4_demo.json \
+    --export_size 2 \
+    --export_legacy_format False