MaziyarPanahi/gemma-7b-alpaca-52k-v0.1

# use google/gemma-7b if you have access
#base_model: mhenrichsen/gemma-7b
base_model: google/gemma-7b
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

hub_model_id: MaziyarPanahi/gemma-7b-alpaca-52k-v0.1
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: true
strict: false

# huggingface repo
datasets:
  - path: tatsu-lab/alpaca
    type: alpaca
val_set_size: 0.1
output_dir: ./qlora-gemma-7b-alpaca

adapter: qlora
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true

sequence_len: 4096
sample_packing: false
pad_to_sequence_len: false

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:


gradient_accumulation_steps: 3
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
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_ratio: 0.1
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM

model_id = "MaziyarPanahi/gemma-7b-alpaca-52k-v0.1"

config = PeftConfig.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")
model = PeftModel.from_pretrained(model, model_id)

# Use a pipeline as a high-level helper
from transformers import pipeline

model_id = "MaziyarPanahi/gemma-7b-alpaca-52k-v0.1"

pipe = pipeline("text-generation", model=model_id)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)