simplify readme

Former-commit-id: 0da6ec2d516326fe9c7583ba71cd1778eb838178

examples/extras/fsdp_qlora/fsdp.sh

@@ -15,11 +15,13 @@ CUDA_VISIBLE_DEVICES=0,1 accelerate launch \
     --overwrite_cache \
     --overwrite_output_dir \
     --cutoff_len 1024 \
+    --preprocessing_num_workers 16 \
     --per_device_train_batch_size 1 \
     --per_device_eval_batch_size 1 \
-    --gradient_accumulation_steps 8 \
+    --gradient_accumulation_steps 4 \
     --lr_scheduler_type cosine \
     --logging_steps 10 \
+    --warmup_steps 20 \
     --save_steps 100 \
     --eval_steps 100 \
     --evaluation_strategy steps \
@@ -28,6 +30,7 @@ CUDA_VISIBLE_DEVICES=0,1 accelerate launch \
     --num_train_epochs 3.0 \
     --max_samples 3000 \
     --val_size 0.1 \
+    --ddp_timeout 180000000 \
     --quantization_bit 4 \
     --plot_loss \
     --fp16

examples/full_multi_gpu/multi_node.sh

@@ -33,6 +33,6 @@ python -m torch.distributed.run \
     --num_train_epochs 3.0 \
     --max_samples 3000 \
     --val_size 0.1 \
-    --ddp_timeout 1800000 \
+    --ddp_timeout 180000000 \
     --plot_loss \
     --fp16

examples/full_multi_gpu/single_node.sh

@@ -27,6 +27,6 @@ deepspeed --num_gpus 4 ../../src/train_bash.py \
     --num_train_epochs 3.0 \
     --max_samples 3000 \
     --val_size 0.1 \
-    --ddp_timeout 1800000 \
+    --ddp_timeout 180000000 \
     --plot_loss \
     --fp16

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

examples/lora_multi_gpu/multi_node.sh

@@ -30,6 +30,6 @@ CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch \
     --num_train_epochs 3.0 \
     --max_samples 3000 \
     --val_size 0.1 \
-    --ddp_timeout 1800000 \
+    --ddp_timeout 180000000 \
     --plot_loss \
     --fp16

examples/lora_multi_gpu/single_node.sh

@@ -30,6 +30,6 @@ CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 accelerate launch \
     --num_train_epochs 3.0 \
     --max_samples 3000 \
     --val_size 0.1 \
-    --ddp_timeout 1800000 \
+    --ddp_timeout 180000000 \
     --plot_loss \
     --fp16

examples/lora_single_gpu/prepare.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES= python ../../src/train_bash.py \
+    --stage sft \
+    --do_train \
+    --model_name_or_path meta-llama/Llama-2-7b-hf \
+    --dataset alpaca_gpt4_en,glaive_toolcall \
+    --dataset_dir ../../data \
+    --template default \
+    --finetuning_type lora \
+    --lora_target q_proj,v_proj \
+    --output_dir ../../saves/LLaMA2-7B/lora/sft \
+    --overwrite_cache \
+    --overwrite_output_dir \
+    --cutoff_len 1024 \
+    --preprocessing_num_workers 16 \
+    --max_samples 3000 \
+    --tokenized_path ../../saves/datasets/sft

examples/merge_lora/README.md

@@ -1,3 +1,12 @@
+> [!WARNING]
+> Merging LoRA weights into a quantized model is not supported.
+
+> [!TIP]
+> Use `--model_name_or_path path_to_model` solely to use the exported model or model fine-tuned in full/freeze mode.
+>
+> Use `CUDA_VISIBLE_DEVICES=0`, `--export_quantization_bit 4` and `--export_quantization_dataset data/c4_demo.json` to quantize the model with AutoGPTQ after merging the LoRA weights.
+
+
 Usage:
 
 - `merge.sh`: merge the lora weights

examples/merge_lora/merge.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 
-CUDA_VISIBLE_DEVICES=0 python ../../src/export_model.py \
+CUDA_VISIBLE_DEVICES= 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 \