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

[model] fix kv cache (#7564)

Browse Source
This commit is contained in:
hoshi-hiyouga
2025-04-01 23:07:46 +08:00
committed by GitHub
parent a13b1bb49a
commit 2bfcad2394
16 changed files with 122 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/accelerate/fsdp_config.yaml
View File

@@ -7,16 +7,16 @@ fsdp_config:
fsdp_backward_prefetch: BACKWARD_PRE
fsdp_forward_prefetch: false
fsdp_cpu_ram_efficient_loading: true
fsdp_offload_params: true # offload may affect training speed
fsdp_offload_params: false
fsdp_sharding_strategy: FULL_SHARD
fsdp_state_dict_type: FULL_STATE_DICT
fsdp_sync_module_states: true
fsdp_use_orig_params: true
machine_rank: 0
main_training_function: main
mixed_precision: bf16 # or fp16
num_machines: 1 # the number of nodes
num_processes: 2 # the number of GPUs in all nodes
mixed_precision: bf16 # or fp16
num_machines: 1 # the number of nodes
num_processes: 2 # the number of GPUs in all nodes
rdzv_backend: static
same_network: true
tpu_env: []