09959fac70
* feat: update mistral common * feat: add mistral3processor * fix: loading * fix: cast pixel_values to fp32 * fix: image tensor conversion * feat: add FA2 support for pixtral based models * fix: update mistral small 3.1 to use native tokenizer * fix: install tips * fix: improve info on sample dataset files * chore: move mistral configs into subfolders * fix: remove unneeded patch * fix: indent * feat: add integration tests * chore: move * feat: add magistral 2509 docs and example * fix: convert tensor to bool * feat: expand tests * chore: move tests
58 lines
1.1 KiB
YAML
58 lines
1.1 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: adamw_bnb_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
bf16: true
|
|
fp16:
|
|
tf32: true
|
|
|
|
gradient_checkpointing: true
|
|
logging_steps: 1
|
|
flash_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
|