1eaf4d7418
* mxfp4 axo * import lint * test for qat mxfp4 * config for mxfp4 * add qat: * pass base config * MXFakeQuantizeConfig * lint * tune config so it fits in 32GB VRAM --------- Co-authored-by: Wing Lian <wing@axolotl.ai>
66 lines
1.2 KiB
YAML
66 lines
1.2 KiB
YAML
base_model: meta-llama/Llama-3.2-3B
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
plugins:
|
|
- axolotl.integrations.liger.LigerPlugin
|
|
|
|
liger_rope: true
|
|
liger_rms_norm: true
|
|
liger_glu_activation: true
|
|
liger_layer_norm: true
|
|
liger_fused_linear_cross_entropy: true
|
|
|
|
datasets:
|
|
- path: yahma/alpaca-cleaned
|
|
type: alpaca
|
|
split: train[:95%]
|
|
|
|
output_dir: ./outputs/qat_out/
|
|
dataset_prepared_path: ./outputs/dataset_prepared
|
|
|
|
sequence_len: 2048
|
|
flash_attention: true
|
|
|
|
qat:
|
|
activation_dtype: mxfp4
|
|
weight_dtype: mxfp4
|
|
group_size: 32
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_checkpointing: true
|
|
activation_offloading: true
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 1
|
|
num_epochs: 1
|
|
optimizer: adamw_torch_8bit
|
|
|
|
cosine_constant_lr_ratio: 0
|
|
cosine_min_lr_ratio: 1.0
|
|
learning_rate: 2e-5
|
|
save_only_model: true
|
|
bf16: true
|
|
|
|
resume_from_checkpoint:
|
|
logging_steps: 1
|
|
|
|
evals_per_epoch: 1
|
|
saves_per_epoch: 1
|
|
|
|
warmup_ratio: 0.1
|
|
weight_decay: 0.0
|
|
|
|
special_tokens:
|
|
pad_token: <|finetune_right_pad_id|>
|
|
|
|
# save_first_step: true # uncomment this to validate checkpoint saving works with your config
|