423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-14 10:56:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

update docs

Browse Source 
Former-commit-id: 34d33e2257
This commit is contained in:
hiyouga
2024-05-06 21:47:00 +08:00
parent 2a53a43ac7
commit eb21a527a6
44 changed files with 487 additions and 516 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
examples/README.md
View File

@@ -1,9 +1,16 @@
We provide diverse examples about fine-tuning LLMs.
```bash
export CUDA_VISIBLE_DEVICES=0
cd examples/lora_single_gpu
llamafactory-cli train llama3_lora_pretrain.yaml # Do continuous pre-training using LoRA
```
```
examples/
├── lora_single_gpu/
│ ├── pretrain.sh: Do continuous pre-training using LoRA
│ ├── `
│ ├── sft.sh: Do supervised fine-tuning using LoRA
│ ├── reward.sh: Do reward modeling using LoRA
│ ├── ppo.sh: Do PPO training using LoRA

2
examples/extras/badam/sft.sh
View File

@@ -10,7 +10,7 @@ CUDA_VISIBLE_DEVICES=0 llamafactory-cli train \
--finetuning_type full \
--use_badam \
--badam_switch_mode descending \
--badam_switch_interval 50 \
--badam_switch_block_every 50 \
--badam_verbose 2 \
--output_dir ../../../saves/LLaMA2-7B/badam/sft \
--overwrite_cache \

7
examples/inference/api_demo.sh
View File

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

7
examples/inference/cli_demo.sh
View File

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

12
examples/inference/evaluate.sh
View File

@@ -1,12 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli eval \
--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

2
examples/inference/llama3.yaml Normal file
View File

@@ -0,0 +1,2 @@
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
template: llama3

4
examples/inference/llama3_lora_sft.yaml Normal file
View File

@@ -0,0 +1,4 @@
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

4
examples/inference/llama3_vllm.yaml Normal file
View File

@@ -0,0 +1,4 @@
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
template: llama3
infer_backend: vllm
vllm_enforce_eager: true

8
examples/inference/web_demo.sh
View File

@@ -1,8 +0,0 @@
#!/bin/bash
# add `--visual_inputs True` to load MLLM
CUDA_VISIBLE_DEVICES=0 llamafactory-cli webchat \
--model_name_or_path meta-llama/Llama-2-7b-hf \
--adapter_name_or_path ../../saves/LLaMA2-7B/lora/sft \
--template default \
--finetuning_type lora

35
examples/lora_single_gpu/dpo.sh
View File

@@ -1,35 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train \
--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

39
examples/lora_single_gpu/llama3_lora_dpo.yaml Normal file
View File

@@ -0,0 +1,39 @@
# model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
# method
stage: dpo
do_train: true
finetuning_type: lora
lora_target: q_proj,v_proj
dpo_ftx: 1.0
# dataset
dataset: orca_rlhf
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
# output
output_dir: saves/llama3-8b/lora/dpo
logging_steps: 10
save_steps: 500
plot_loss: true
overwrite_output_dir: true
# train
per_device_train_batch_size: 1
gradient_accumulation_steps: 8
learning_rate: 0.00001
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_steps: 0.1
fp16: true
# eval
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

19
examples/lora_single_gpu/llama3_lora_eval.yaml Normal file
View File

@@ -0,0 +1,19 @@
# model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
adapter_name_or_path: saves/llama3-8b/lora/sft
# method
finetuning_type: lora
# dataset
task: mmlu
split: test
template: fewshot
lang: en
n_shot: 5
# output
save_dir: saves/llama3-8b/lora/eval
# eval
batch_size: 4

38
examples/lora_single_gpu/llama3_lora_orpo.yaml Normal file
View File

@@ -0,0 +1,38 @@
# model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
# method
stage: orpo
do_train: true
finetuning_type: lora
lora_target: q_proj,v_proj
# dataset
dataset: orca_rlhf
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
# output
output_dir: saves/llama3-8b/lora/orpo
logging_steps: 10
save_steps: 500
plot_loss: true
overwrite_output_dir: true
# train
per_device_train_batch_size: 1
gradient_accumulation_steps: 8
learning_rate: 0.00001
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_steps: 0.1
fp16: true
# eval
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

38
examples/lora_single_gpu/llama3_lora_ppo.yaml Normal file
View File

@@ -0,0 +1,38 @@
# model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
reward_model: saves/llama3-8b/lora/reward
# method
stage: ppo
do_train: true
finetuning_type: lora
lora_target: q_proj,v_proj
# dataset
dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
overwrite_cache: true
preprocessing_num_workers: 16
# output
output_dir: saves/llama3-8b/lora/ppo
logging_steps: 10
save_steps: 500
plot_loss: true
overwrite_output_dir: true
# train
per_device_train_batch_size: 1
gradient_accumulation_steps: 8
learning_rate: 0.00001
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_steps: 0.1
fp16: true
# generate
max_new_tokens: 512
top_k: 0
top_p: 0.9

24
examples/lora_single_gpu/llama3_lora_predict.yaml Normal file
View File

@@ -0,0 +1,24 @@
# model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
adapter_name_or_path: saves/llama3-8b/lora/sft
# method
stage: sft
do_predict: true
finetuning_type: lora
# dataset
dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 50
overwrite_cache: true
preprocessing_num_workers: 16
# output
output_dir: saves/llama3-8b/lora/predict
overwrite_output_dir: true
# eval
per_device_eval_batch_size: 1
predict_with_generate: true

37
examples/lora_single_gpu/llama3_lora_pretrain.yaml Normal file
View File

@@ -0,0 +1,37 @@
# model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
# method
stage: pt
do_train: true
finetuning_type: lora
lora_target: q_proj,v_proj
# dataset
dataset: c4_demo
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
# output
output_dir: saves/llama3-8b/lora/sft
logging_steps: 10
save_steps: 500
plot_loss: true
overwrite_output_dir: true
# train
per_device_train_batch_size: 1
gradient_accumulation_steps: 8
learning_rate: 0.0001
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_steps: 0.1
fp16: true
# eval
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

38
examples/lora_single_gpu/llama3_lora_reward.yaml Normal file
View File

@@ -0,0 +1,38 @@
# model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
# method
stage: rm
do_train: true
finetuning_type: lora
lora_target: q_proj,v_proj
# dataset
dataset: orca_rlhf
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
# output
output_dir: saves/llama3-8b/lora/reward
logging_steps: 10
save_steps: 500
plot_loss: true
overwrite_output_dir: true
# train
per_device_train_batch_size: 1
gradient_accumulation_steps: 8
learning_rate: 0.00001
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_steps: 0.1
fp16: true
# eval
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

38
examples/lora_single_gpu/llama3_lora_sft.yaml Normal file
View File

@@ -0,0 +1,38 @@
# model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
# method
stage: sft
do_train: true
finetuning_type: lora
lora_target: q_proj,v_proj
# dataset
dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
# output
output_dir: saves/llama3-8b/lora/sft
logging_steps: 10
save_steps: 500
plot_loss: true
overwrite_output_dir: true
# train
per_device_train_batch_size: 1
gradient_accumulation_steps: 8
learning_rate: 0.0001
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_steps: 0.1
fp16: true
# eval
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

22
examples/lora_single_gpu/llama3_preprocess.yaml Normal file
View File

@@ -0,0 +1,22 @@
# model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
# method
stage: sft
do_train: true
finetuning_type: lora
lora_target: q_proj,v_proj
# dataset
dataset: identity,alpaca_gpt4_en
template: llama3
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
tokenized_path: saves/llama3-8b/dataset/sft # use `tokenized_path` in config to load data
# output
output_dir: saves/llama3-8b/lora/sft
overwrite_output_dir: true

39
examples/lora_single_gpu/llava1_5_lora_sft.yaml Normal file
View File

@@ -0,0 +1,39 @@
# model
model_name_or_path: llava-hf/llava-1.5-7b-hf
visual_inputs: true
# method
stage: sft
do_train: true
finetuning_type: lora
lora_target: q_proj,v_proj
# dataset
dataset: mllm_demo
template: vicuna
cutoff_len: 1024
max_samples: 1000
val_size: 0.1
overwrite_cache: true
preprocessing_num_workers: 16
# output
output_dir: saves/llava1_5-7b/lora/sft
logging_steps: 10
save_steps: 500
plot_loss: true
overwrite_output_dir: true
# train
per_device_train_batch_size: 1
gradient_accumulation_steps: 8
learning_rate: 0.0001
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_steps: 0.1
fp16: true
# eval
per_device_eval_batch_size: 1
evaluation_strategy: steps
eval_steps: 500

32
examples/lora_single_gpu/orpo.sh
View File

@@ -1,32 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train \
--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

32
examples/lora_single_gpu/ppo.sh
View File

@@ -1,32 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train \
--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

19
examples/lora_single_gpu/predict.sh
View File

@@ -1,19 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train \
--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

19
examples/lora_single_gpu/prepare.sh
View File

@@ -1,19 +0,0 @@
#!/bin/bash
# use `--tokenized_path` in training script to load data
CUDA_VISIBLE_DEVICES= llamafactory-cli train \
--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

31
examples/lora_single_gpu/pretrain.sh
View File

@@ -1,31 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train \
--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

33
examples/lora_single_gpu/reward.sh
View File

@@ -1,33 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train \
--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

32
examples/lora_single_gpu/sft.sh
View File

@@ -1,32 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train \
--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

33
examples/lora_single_gpu/sft_mllm.sh
View File

@@ -1,33 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train \
--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

11
examples/merge_lora/llama3_gptq.yaml Normal file
View File

@@ -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

13
examples/merge_lora/llama3_lora_sft.yaml Normal file
View File

@@ -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

12
examples/merge_lora/merge.sh
View File

@@ -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

11
examples/merge_lora/quantize.sh
View File

@@ -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

30
examples/qlora_single_gpu/aqlm.sh
View File

@@ -1,30 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train \
--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

30
examples/qlora_single_gpu/awq.sh
View File

@@ -1,30 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train \
--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

31
examples/qlora_single_gpu/bitsandbytes.sh
View File

@@ -1,31 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train \
--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 \
--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 \
--quantization_bit 4 \
--plot_loss \
--fp16

30
examples/qlora_single_gpu/gptq.sh
View File

@@ -1,30 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 llamafactory-cli train \
--stage sft \
--do_train \
--model_name_or_path TheBloke/Llama-2-7B-GPTQ \
--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

27
examples/qlora_single_gpu/llama3_lora_sft_aqlm.yaml Normal file
View File

@@ -0,0 +1,27 @@
stage: sft
do_train: true
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: true
overwrite_output_dir: true
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: true
learning_rate: 5e-5
num_train_epochs: 3.0
max_samples: 3000
val_size: 0.1
plot_loss: true
fp16: true

0
examples/qlora_single_gpu/llama3_lora_sft_awq.yaml Normal file
View File

0
examples/qlora_single_gpu/llama3_lora_sft_bitsandbytes.yaml Normal file
View File

0
examples/qlora_single_gpu/llama3_lora_sft_gptq.yaml Normal file
View File