Files
axolotl/examples/apertus/apertus-8b-qlora.yaml
NanoCode012 c51d6b06c3 feat: add apertus model and cce (#3144) [skip ci]
* feat: add apertus, glm4v, glm4v_moe cce

* fix: arcee docs

* feat: add apertus

* feat: added vram usage

* fix: add apertus note

* feat: update doc on apertus xielu

* fix: add monkeypatch for xielu activation issue

* fix: simplify env

* feat: pin commit

* feat: add packing

* chore: move patch calling

* Update examples/apertus/README.md

Co-authored-by: salman <salman.mohammadi@outlook.com>

* Update examples/apertus/README.md

Co-authored-by: salman <salman.mohammadi@outlook.com>

* Update examples/apertus/README.md

Co-authored-by: salman <salman.mohammadi@outlook.com>

---------

Co-authored-by: salman <salman.mohammadi@outlook.com>
2025-09-19 17:34:04 +07:00

65 lines
1.1 KiB
YAML

base_model: swiss-ai/Apertus-8B-Instruct-2509
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name
plugins:
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
load_in_8bit: false
load_in_4bit: 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/lora-out
adapter: qlora
lora_model_dir:
sequence_len: 2048
sample_packing: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_target_modules:
- gate_proj
- down_proj
- up_proj
- q_proj
- v_proj
- k_proj
- o_proj
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_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
# save_first_step: true # uncomment this to validate checkpoint saving works with your config