Initial commit

LLaMA-Factory/examples/inference/api_demo.sh

+#!/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

LLaMA-Factory/examples/inference/cli_demo.sh

+#!/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

LLaMA-Factory/examples/inference/evaluate.sh

+#!/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 fewshot \
+    --finetuning_type lora \
+    --task mmlu \
+    --split test \
+    --lang en \
+    --n_shot 5 \
+    --batch_size 4

LLaMA-Factory/examples/inference/web_demo.sh

+#!/bin/bash
+# add `--visual_inputs True` to load MLLM
+
+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

LLaMA-Factory/examples/lora_multi_gpu/ds_zero3.sh

+#!/bin/bash
+
+deepspeed --num_gpus 4 ../../src/train_bash.py \
+    --deepspeed ../deepspeed/ds_z3_config.json \
+    --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 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --gradient_accumulation_steps 2 \
+    --lr_scheduler_type cosine \
+    --logging_steps 10 \
+    --warmup_steps 20 \
+    --save_steps 100 \
+    --eval_steps 100 \
+    --evaluation_strategy steps \
+    --learning_rate 5e-5 \
+    --num_train_epochs 3.0 \
+    --max_samples 3000 \
+    --val_size 0.1 \
+    --ddp_timeout 180000000 \
+    --plot_loss \
+    --fp16

LLaMA-Factory/examples/lora_multi_gpu/multi_node.sh

+#!/bin/bash
+# also launch it on slave machine using slave_config.yaml
+
+CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch \
+    --config_file ../accelerate/master_config.yaml \
+    ../../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 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --gradient_accumulation_steps 2 \
+    --lr_scheduler_type cosine \
+    --logging_steps 10 \
+    --warmup_steps 20 \
+    --save_steps 100 \
+    --eval_steps 100 \
+    --evaluation_strategy steps \
+    --load_best_model_at_end \
+    --learning_rate 5e-5 \
+    --num_train_epochs 3.0 \
+    --max_samples 3000 \
+    --val_size 0.1 \
+    --ddp_timeout 180000000 \
+    --plot_loss \
+    --fp16

LLaMA-Factory/examples/lora_multi_gpu/single_node.sh

+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch \
+    --config_file ../accelerate/single_config.yaml \
+    ../../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 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --gradient_accumulation_steps 2 \
+    --lr_scheduler_type cosine \
+    --logging_steps 10 \
+    --warmup_steps 20 \
+    --save_steps 100 \
+    --eval_steps 100 \
+    --evaluation_strategy steps \
+    --load_best_model_at_end \
+    --learning_rate 5e-5 \
+    --num_train_epochs 3.0 \
+    --max_samples 3000 \
+    --val_size 0.1 \
+    --ddp_timeout 180000000 \
+    --plot_loss \
+    --fp16

LLaMA-Factory/examples/lora_single_gpu/dpo.sh

+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
+    --stage dpo \
+    --do_train \
+    --model_name_or_path meta-llama/Llama-2-7b-hf \
+    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
+    --create_new_adapter \
+    --dataset orca_rlhf \
+    --dataset_dir ../../data \
+    --template default \
+    --finetuning_type lora \
+    --lora_target q_proj,v_proj \
+    --output_dir ../../saves/LLaMA2-7B/lora/dpo \
+    --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 \
+    --lr_scheduler_type cosine \
+    --logging_steps 10 \
+    --warmup_steps 20 \
+    --save_steps 100 \
+    --eval_steps 100 \
+    --evaluation_strategy steps \
+    --load_best_model_at_end \
+    --learning_rate 1e-5 \
+    --num_train_epochs 1.0 \
+    --max_samples 1000 \
+    --val_size 0.1 \
+    --dpo_ftx 1.0 \
+    --plot_loss \
+    --fp16

LLaMA-Factory/examples/lora_single_gpu/orpo.sh

+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
+    --stage orpo \
+    --do_train \
+    --model_name_or_path meta-llama/Llama-2-7b-hf \
+    --dataset orca_rlhf \
+    --dataset_dir ../../data \
+    --template default \
+    --finetuning_type lora \
+    --lora_target q_proj,v_proj \
+    --output_dir ../../saves/LLaMA2-7B/lora/orpo \
+    --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 \
+    --lr_scheduler_type cosine \
+    --logging_steps 10 \
+    --warmup_steps 20 \
+    --save_steps 100 \
+    --eval_steps 100 \
+    --evaluation_strategy steps \
+    --load_best_model_at_end \
+    --learning_rate 1e-5 \
+    --num_train_epochs 1.0 \
+    --max_samples 1000 \
+    --val_size 0.1 \
+    --plot_loss \
+    --fp16

LLaMA-Factory/examples/lora_single_gpu/ppo.sh

+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
+    --stage ppo \
+    --do_train \
+    --model_name_or_path meta-llama/Llama-2-7b-hf \
+    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
+    --create_new_adapter \
+    --dataset alpaca_gpt4_en \
+    --dataset_dir ../../data \
+    --template default \
+    --finetuning_type lora \
+    --lora_target q_proj,v_proj \
+    --reward_model ../../saves/LLaMA2-7B/lora/reward \
+    --output_dir ../../saves/LLaMA2-7B/lora/ppo \
+    --overwrite_cache \
+    --overwrite_output_dir \
+    --cutoff_len 512 \
+    --preprocessing_num_workers 16 \
+    --per_device_train_batch_size 1 \
+    --gradient_accumulation_steps 8 \
+    --lr_scheduler_type cosine \
+    --logging_steps 10 \
+    --save_steps 100 \
+    --learning_rate 1e-5 \
+    --num_train_epochs 1.0 \
+    --max_samples 1000 \
+    --top_k 0 \
+    --top_p 0.9 \
+    --max_new_tokens 256 \
+    --plot_loss \
+    --fp16

LLaMA-Factory/examples/lora_single_gpu/predict.sh

+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
+    --stage sft \
+    --do_predict \
+    --model_name_or_path meta-llama/Llama-2-7b-hf \
+    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft,../../saves/LLaMA2-7B/lora/dpo \
+    --dataset alpaca_gpt4_en,glaive_toolcall \
+    --dataset_dir ../../data \
+    --template default \
+    --finetuning_type lora \
+    --output_dir ../../saves/LLaMA2-7B/lora/predict \
+    --overwrite_cache \
+    --overwrite_output_dir \
+    --cutoff_len 1024 \
+    --preprocessing_num_workers 16 \
+    --per_device_eval_batch_size 1 \
+    --max_samples 20 \
+    --predict_with_generate

LLaMA-Factory/examples/lora_single_gpu/prepare.sh

+#!/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

LLaMA-Factory/examples/lora_single_gpu/pretrain.sh

+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
+    --stage pt \
+    --do_train \
+    --model_name_or_path meta-llama/Llama-2-7b-hf \
+    --dataset c4_demo \
+    --dataset_dir ../../data \
+    --finetuning_type lora \
+    --lora_target q_proj,v_proj \
+    --output_dir ../../saves/LLaMA2-7B/lora/pretrain \
+    --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 \
+    --lr_scheduler_type cosine \
+    --logging_steps 10 \
+    --warmup_steps 20 \
+    --save_steps 100 \
+    --eval_steps 100 \
+    --evaluation_strategy steps \
+    --load_best_model_at_end \
+    --learning_rate 5e-5 \
+    --num_train_epochs 3.0 \
+    --max_samples 10000 \
+    --val_size 0.1 \
+    --plot_loss \
+    --fp16

LLaMA-Factory/examples/lora_single_gpu/reward.sh

+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
+    --stage rm \
+    --do_train \
+    --model_name_or_path meta-llama/Llama-2-7b-hf \
+    --adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
+    --create_new_adapter \
+    --dataset orca_rlhf \
+    --dataset_dir ../../data \
+    --template default \
+    --finetuning_type lora \
+    --lora_target q_proj,v_proj \
+    --output_dir ../../saves/LLaMA2-7B/lora/reward \
+    --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 \
+    --lr_scheduler_type cosine \
+    --logging_steps 10 \
+    --warmup_steps 20 \
+    --save_steps 100 \
+    --eval_steps 100 \
+    --evaluation_strategy steps \
+    --learning_rate 1e-5 \
+    --num_train_epochs 1.0 \
+    --max_samples 5000 \
+    --val_size 0.1 \
+    --plot_loss \
+    --fp16

LLaMA-Factory/examples/lora_single_gpu/sft.sh

+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0 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 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --gradient_accumulation_steps 8 \
+    --lr_scheduler_type cosine \
+    --logging_steps 10 \
+    --warmup_steps 20 \
+    --save_steps 100 \
+    --eval_steps 100 \
+    --evaluation_strategy steps \
+    --load_best_model_at_end \
+    --learning_rate 5e-5 \
+    --num_train_epochs 3.0 \
+    --max_samples 3000 \
+    --val_size 0.1 \
+    --plot_loss \
+    --fp16

LLaMA-Factory/examples/lora_single_gpu/sft_mllm.sh

+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
+    --stage sft \
+    --do_train \
+    --model_name_or_path llava-hf/llava-1.5-7b-hf \
+    --visual_inputs \
+    --dataset mllm_demo \
+    --dataset_dir ../../data \
+    --template vicuna \
+    --finetuning_type lora \
+    --lora_target q_proj,v_proj \
+    --output_dir ../../saves/LLaMA2-7B/lora/sft_mllm \
+    --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 \
+    --lr_scheduler_type cosine \
+    --logging_steps 10 \
+    --warmup_steps 20 \
+    --save_steps 100 \
+    --eval_steps 100 \
+    --evaluation_strategy steps \
+    --load_best_model_at_end \
+    --learning_rate 5e-5 \
+    --num_train_epochs 100.0 \
+    --max_samples 3000 \
+    --val_size 0.1 \
+    --plot_loss \
+    --fp16

LLaMA-Factory/examples/merge_lora/merge.sh

+#!/bin/bash
+# DO NOT use quantized model or quantization_bit when merging lora weights
+
+CUDA_VISIBLE_DEVICES=0 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_device cpu \
+    --export_legacy_format False

LLaMA-Factory/examples/merge_lora/quantize.sh

+#!/bin/bash
+# NEED TO run `merge.sh` before using this script
+
+CUDA_VISIBLE_DEVICES=0 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

LLaMA-Factory/examples/qlora_single_gpu/aqlm.sh

+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
+    --stage sft \
+    --do_train \
+    --model_name_or_path BlackSamorez/Llama-2-7b-AQLM-2Bit-1x16-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 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --gradient_accumulation_steps 8 \
+    --lr_scheduler_type cosine \
+    --logging_steps 10 \
+    --save_steps 100 \
+    --eval_steps 100 \
+    --evaluation_strategy steps \
+    --load_best_model_at_end \
+    --learning_rate 5e-5 \
+    --num_train_epochs 3.0 \
+    --max_samples 3000 \
+    --val_size 0.1 \
+    --plot_loss \
+    --fp16

LLaMA-Factory/examples/qlora_single_gpu/awq.sh

+#!/bin/bash
+
+CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
+    --stage sft \
+    --do_train \
+    --model_name_or_path TheBloke/Llama-2-7B-AWQ \
+    --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 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 1 \
+    --gradient_accumulation_steps 8 \
+    --lr_scheduler_type cosine \
+    --logging_steps 10 \
+    --save_steps 100 \
+    --eval_steps 100 \
+    --evaluation_strategy steps \
+    --load_best_model_at_end \
+    --learning_rate 5e-5 \
+    --num_train_epochs 3.0 \
+    --max_samples 3000 \
+    --val_size 0.1 \
+    --plot_loss \
+    --fp16