Files
axolotl/examples/magistral/think/magistral-small-think-qlora.yaml
NanoCode012 09959fac70 Feat: add Magistral Small 2509 and native mistral3 tokenizer support (#3165)
* 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
2025-09-18 15:42:20 +07:00

68 lines
1.2 KiB
YAML

base_model: mistralai/Magistral-Small-2507
# Enable to use mistral-common tokenizer
tokenizer_use_mistral_common: true
# 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: Nanobit/text-think-2k-test
type: chat_template
dataset_prepared_path: last_run_prepared
val_set_size: 0
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