ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support fsdp + qlora

Browse Source 
Former-commit-id: b894bf8e84be689db258021f0638e9ac939abcbc
This commit is contained in:
hiyouga
2024-03-21 00:36:06 +08:00
parent 5ed234ca63
commit 935ee0a023
15 changed files with 87 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
examples/accelerate/fsdp_config.yaml Normal file
View File

@@ -0,0 +1,25 @@
compute_environment: LOCAL_MACHINE
debug: false
distributed_type: FSDP
downcast_bf16: 'no'
fsdp_config:
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
fsdp_backward_prefetch: BACKWARD_PRE
fsdp_cpu_ram_efficient_loading: true
fsdp_forward_prefetch: false
fsdp_offload_params: true
fsdp_sharding_strategy: FULL_SHARD
fsdp_state_dict_type: SHARDED_STATE_DICT
fsdp_sync_module_states: true
fsdp_use_orig_params: false
machine_rank: 0
main_training_function: main
mixed_precision: fp16
num_machines: 1
num_processes: 2
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false

18
examples/accelerate/master_config.yaml Normal file
View File

@@ -0,0 +1,18 @@
compute_environment: LOCAL_MACHINE
debug: false
distributed_type: MULTI_GPU
downcast_bf16: 'no'
gpu_ids: all
machine_rank: 0
main_process_ip: 192.168.0.1
main_process_port: 29555
main_training_function: main
mixed_precision: fp16
num_machines: 2
num_processes: 16
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false

16
examples/accelerate/single_config.yaml Normal file
View File

@@ -0,0 +1,16 @@
compute_environment: LOCAL_MACHINE
debug: false
distributed_type: MULTI_GPU
downcast_bf16: 'no'
gpu_ids: all
machine_rank: 0
main_training_function: main
mixed_precision: fp16
num_machines: 1
num_processes: 4
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false

18
examples/accelerate/slave_config.yaml Normal file
View File

@@ -0,0 +1,18 @@
compute_environment: LOCAL_MACHINE
debug: false
distributed_type: MULTI_GPU
downcast_bf16: 'no'
gpu_ids: all
machine_rank: 1
main_process_ip: 192.168.0.1
main_process_port: 29555
main_training_function: main
mixed_precision: fp16
num_machines: 2
num_processes: 16
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false