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
86 lines
1.7 KiB
YAML
86 lines
1.7 KiB
YAML
base_model: mistralai/Mixtral-8x7B-v0.1
|
|
# optionally might have model_type or tokenizer_type
|
|
model_type: AutoModelForCausalLM
|
|
tokenizer_type: LlamaTokenizer
|
|
# Automatically upload checkpoint and final model to HF
|
|
# hub_model_id: username/custom_model_name
|
|
|
|
trust_remote_code: true
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: true
|
|
|
|
datasets:
|
|
- path: tatsu-lab/alpaca
|
|
type: alpaca
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0.0
|
|
output_dir: ./outputs/qlora-out
|
|
|
|
## You can optionally freeze the entire model and unfreeze a subset of parameters
|
|
unfrozen_parameters:
|
|
# - ^lm_head.weight$
|
|
# - ^model.embed_tokens.weight$[:32000]
|
|
# - model.layers.2[0-9]+.block_sparse_moe.gate
|
|
# - model.layers.2[0-9]+.block_sparse_moe.experts
|
|
# - model.layers.3[0-9]+.block_sparse_moe.gate
|
|
# - model.layers.3[0-9]+.block_sparse_moe.experts
|
|
|
|
model_config:
|
|
output_router_logits: true
|
|
|
|
adapter: qlora
|
|
lora_model_dir:
|
|
|
|
sequence_len: 4096
|
|
sample_packing: true
|
|
|
|
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_linear: true
|
|
#lora_target_modules:
|
|
# - gate
|
|
# - q_proj
|
|
# - k_proj
|
|
# - v_proj
|
|
# - o_proj
|
|
# - w1
|
|
# - w2
|
|
# - w3
|
|
|
|
wandb_project:
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_name:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 2
|
|
micro_batch_size: 1
|
|
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
|
|
|
|
loss_watchdog_threshold: 5.0
|
|
loss_watchdog_patience: 3
|
|
|
|
warmup_ratio: 0.1
|
|
evals_per_epoch: 4
|
|
saves_per_epoch: 1
|
|
|
|
deepspeed: deepspeed_configs/zero2.json
|
|
weight_decay: 0.0
|
|
special_tokens:
|
|
|
|
# save_first_step: true # uncomment this to validate checkpoint saving works with your config
|