pip install peft

pip install git+https://github.com/huggingface/peft.git

from transformers import AutoModelForCausalLM, AutoTokenizer

peft_model_id = "ybelkada/opt-350m-lora"
model = AutoModelForCausalLM.from_pretrained(peft_model_id)

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "facebook/opt-350m"
peft_model_id = "ybelkada/opt-350m-lora"

model = AutoModelForCausalLM.from_pretrained(model_id)
model.load_adapter(peft_model_id)

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig

peft_model_id = "ybelkada/opt-350m-lora"
model = AutoModelForCausalLM.from_pretrained(peft_model_id, quantization_config=BitsAndBytesConfig(load_in_8bit=True))

from transformers import AutoModelForCausalLM, OPTForCausalLM, AutoTokenizer
from peft import PeftConfig

model_id = "facebook/opt-350m"
model = AutoModelForCausalLM.from_pretrained(model_id)

lora_config = LoraConfig(
    target_modules=["q_proj", "k_proj"],
    init_lora_weights=False
)

model.add_adapter(lora_config, adapter_name="adapter_1")

# attach new adapter with same config
model.add_adapter(lora_config, adapter_name="adapter_2")

# use adapter_1
model.set_adapter("adapter_1")
output = model.generate(**inputs)
print(tokenizer.decode(output_disabled[0], skip_special_tokens=True))

# use adapter_2
model.set_adapter("adapter_2")
output_enabled = model.generate(**inputs)
print(tokenizer.decode(output_enabled[0], skip_special_tokens=True))

from transformers import AutoModelForCausalLM, OPTForCausalLM, AutoTokenizer
from peft import PeftConfig

model_id = "facebook/opt-350m"
adapter_model_id = "ybelkada/opt-350m-lora"
tokenizer = AutoTokenizer.from_pretrained(model_id)
text = "Hello"
inputs = tokenizer(text, return_tensors="pt")

model = AutoModelForCausalLM.from_pretrained(model_id)
peft_config = PeftConfig.from_pretrained(adapter_model_id)

# to initiate with random weights
peft_config.init_lora_weights = False

model.add_adapter(peft_config)
model.enable_adapters()
output = model.generate(**inputs)

model.disable_adapters()
output = model.generate(**inputs)

from peft import LoraConfig

peft_config = LoraConfig(
    lora_alpha=16,
    lora_dropout=0.1,
    r=64,
    bias="none",
    task_type="CAUSAL_LM",
)

model.add_adapter(peft_config)

trainer = Trainer(model=model, ...)
trainer.train()

model.save_pretrained(save_dir)
model = AutoModelForCausalLM.from_pretrained(save_dir)