Example notebook for running Axolotl on google colab

import torch
# Check so there is a gpu available, a T4(free tier) is enough to run this notebook
assert (torch.cuda.is_available()==True)

Install Axolotl and dependencies

!pip install -e git+https://github.com/axolotl-ai-cloud/axolotl#egg=axolotl
!pip install flash-attn=="2.5.0"
!pip install deepspeed=="0.13.1"!pip install mlflow=="2.13.0"

Create an yaml config file

import yaml

# Your YAML string
yaml_string = """
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/qlora-out

adapter: qlora
lora_model_dir:

sequence_len: 4096
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

"""

# Convert the YAML string to a Python dictionary
yaml_dict = yaml.safe_load(yaml_string)

# Specify your file path
file_path = 'test_axolotl.yaml'

# Write the YAML file
with open(file_path, 'w') as file:
    yaml.dump(yaml_dict, file)

Launch the training

# By using the ! the comand will be executed as a bash command
!accelerate launch -m axolotl.cli.train /content/test_axolotl.yaml

Play with inference

# By using the ! the comand will be executed as a bash command
!accelerate launch -m axolotl.cli.inference /content/test_axolotl.yaml \
    --qlora_model_dir="./qlora-out" --gradio