mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2026-05-05 07:38:55 +08:00
887ee2b121
Co-authored-by: mrhaoxx <mr.haoxx@gmail.com> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
26 lines
677 B
YAML
26 lines
677 B
YAML
compute_environment: LOCAL_MACHINE
|
|
distributed_type: FSDP
|
|
fsdp_config:
|
|
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
|
|
fsdp_cpu_ram_efficient_loading: true
|
|
fsdp_offload_params: false
|
|
fsdp_reshard_after_forward: true
|
|
fsdp_state_dict_type: FULL_STATE_DICT
|
|
fsdp_version: 2
|
|
mixed_precision: bf16
|
|
num_machines: 1
|
|
num_processes: 4 # Adjust based on your GPU count; 4 is suitable for 4 GPUs
|
|
rdzv_backend: static
|
|
same_network: true
|
|
use_cpu: false
|
|
|
|
kt_config:
|
|
enabled: true
|
|
kt_backend: AMXBF16 # Use with original BF16 expert weights.
|
|
kt_num_threads: 96
|
|
kt_tp_enabled: true
|
|
kt_threadpool_count: 2
|
|
kt_max_cache_depth: 2
|
|
kt_share_backward_bb: true
|
|
lora_rank: 8
|