dfba881e99
* feat: add gemma3n cce
* feat: add sample config
* feat: add gemma3n multimodal mode
* feat: add audio example
* feat: support audio and return pixel values in collator
* feat: support unmask only assistant region (gemma3n for now)
* feat(doc): add notes for audio loading
* feat: add audio support for gemma3n
* feat: update examples
* feat: add gemma3n to the docs
* fix: add link at top
* feat(doc): clarify additional requirements
* fix: mllama missing aspect ratio
* fix: mllama need attention fixes for fa2
* Partially Revert "fix: mllama need attention fixes for fa2"
This reverts commit a0bfdd1777.
* fix: disable FA2 for mllama in vision mode
* feat: update configs to use proper attention
* fix: support other vision features
* feat(doc): clarify requirements for gemma3n
59 lines
1.2 KiB
YAML
59 lines
1.2 KiB
YAML
base_model: mistral-community/pixtral-12b
|
|
processor_type: AutoProcessor
|
|
|
|
# these 3 lines are needed for now to handle vision chat templates w images
|
|
skip_prepare_dataset: true
|
|
remove_unused_columns: false
|
|
sample_packing: false
|
|
|
|
chat_template: pixtral
|
|
datasets:
|
|
- path: HuggingFaceH4/llava-instruct-mix-vsft
|
|
type: chat_template
|
|
split: train[:1%]
|
|
dataset_prepared_path:
|
|
val_set_size: 0.0
|
|
output_dir: ./outputs/out
|
|
|
|
adapter: lora
|
|
lora_model_dir:
|
|
|
|
sequence_len: 8192
|
|
pad_to_sequence_len: false
|
|
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_modules: 'model.language_model.layers.[\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj'
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 1
|
|
num_epochs: 1
|
|
optimizer: muon
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
bf16: true
|
|
fp16:
|
|
tf32: true
|
|
|
|
gradient_checkpointing: true
|
|
logging_steps: 1
|
|
# flash_attention: # PixtralVisionModel does not support Flash Attention 2.0 yet
|
|
sdp_attention: true
|
|
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch: 1
|
|
saves_per_epoch: 1
|
|
weight_decay: 0.0
|
|
special_tokens:
|
|
pad_token: <pad>
|
|
|
|
# save_first_step: true # uncomment this to validate checkpoint saving works with your config
|