945c8aeb10
* fix: saving clones state dict
* fix: apply fix for only CP mode
* fix: add dropout check when using lora target param
* fix: re-add patch from transformers PR #39866
* feat: add moe quant to test by ved
* fix: try match target param properly end with
* fix: clear cache per param quant
* fix: attempt on-load quantize experts instead of post-load
* fix: attempt disable async load
* chore: add log
* chore: adjust log
* fix: remove cuda alloc for moe and enable async load
* chore: remove leftover logs
* chore: add extra empty cache
* fix(doc): clarify support
* fix: handle fsdp2 for paramwrapper dtensor
* feat: attempt to quant experts in 8bit mode too
* feat: attempt to release bf16 experts from vram
* feat: upgrade cce
* fix: fsdp2 init_sharded_param load int8/uint4 dtensor as
require_grad=true on init
* fix: remove unnecessary gc and empty cache
* Revert "fix: remove unnecessary gc and empty cache"
This reverts commit 1d54518990.
* fix: do not call full_tensor on non-dtensors
* fix: attempt to address fsdp2 with quant exp high loss
* fix: attempt lora quant experts wrong dim
* fix: ensure require_grad patch applied for lora 8bit
* fix: attempt lora 8bit fsdp2
* fix: attribute access on save for lora 8bit fsdp2
* fix: wrong weight attrib access
* chore(refactor): add config, re-arrange position of patches, clean
comments
* feat: add example docs
* chore: cherry pick trinity fixes from PR 3399
* chore: comments refactor; add guards
* fix: guard using wrong key
* fix: mamba save does not accept main process param
* fix: guard prevent double hook
* fix: move gc to upper scope
* chore: add comment on proxy forward patch
* fix: add comment to clarify
* feat: add test idempotency
* fix: AttributeError: `e_score_correction_bias` is not an nn.Parameter
* fix: AttributeError: 'NoneType' object has no attribute 'to'
* fix: update docs on cpu_ram_efficient_loading
66 lines
1.1 KiB
YAML
66 lines
1.1 KiB
YAML
base_model: zai-org/GLM-4.7-Flash
|
|
|
|
plugins:
|
|
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
|
|
|
load_in_8bit: true
|
|
quantize_moe_experts: true
|
|
|
|
datasets:
|
|
- path: fozziethebeat/alpaca_messages_2k_test
|
|
type: chat_template
|
|
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.1
|
|
output_dir: ./outputs/glm4.7-flash-lora-8bit-out
|
|
|
|
adapter: lora
|
|
lora_model_dir:
|
|
|
|
sequence_len: 2048
|
|
sample_packing: true
|
|
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0
|
|
lora_target_modules:
|
|
- q_proj
|
|
- v_proj
|
|
- k_proj
|
|
- o_proj
|
|
|
|
# Uncomment to also target MoE expert weights:
|
|
# lora_target_parameters:
|
|
# - mlp.experts.gate_up_proj
|
|
# - mlp.experts.down_proj
|
|
|
|
# LoRA kernels incompatible with DSA attention
|
|
lora_mlp_kernel: false
|
|
lora_qkv_kernel: false
|
|
lora_o_kernel: false
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 2
|
|
num_epochs: 1
|
|
optimizer: adamw_torch_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
bf16: auto
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch: 1
|
|
saves_per_epoch: 1
|