update docs

Former-commit-id: a4a2e94241bea6f96590f6cb8ca8b5cddee1917e

examples/merge_lora/llama3_gptq.yaml

@@ -0,0 +1,11 @@
+# model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+template: llama3
+
+# export
+export_dir: models/llama3_gptq
+export_quantization_bit: 4
+export_quantization_dataset: data/c4_demo.json
+export_size: 2
+export_device: cpu
+export_legacy_format: false

examples/merge_lora/llama3_lora_sft.yaml

@@ -0,0 +1,13 @@
+# Note: DO NOT use quantized model or quantization_bit when merging lora weights
+
+# model
+model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
+adapter_name_or_path: saves/llama3-8b/lora/sft
+template: llama3
+finetuning_type: lora
+
+# export
+export_dir: models/llama3_lora_sft
+export_size: 2
+export_device: cpu
+export_legacy_format: false

examples/merge_lora/merge.sh

@@ -1,12 +0,0 @@
-#!/bin/bash
-# DO NOT use quantized model or quantization_bit when merging lora weights
-
-CUDA_VISIBLE_DEVICES=0 llamafactory-cli export \
-    --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_device cpu \
-    --export_legacy_format False

examples/merge_lora/quantize.sh

@@ -1,11 +0,0 @@
-#!/bin/bash
-# NEED TO run `merge.sh` before using this script
-
-CUDA_VISIBLE_DEVICES=0 llamafactory-cli export \
-    --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