Llama 3 8B API Migration

Official adapter · maintained by LoRADock

Produces incremental API migration plans with compatibility checks, deprecation notes, and test updates.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
base = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
model = PeftModel.from_pretrained(base, "loradock/llama3-8b-api-migration")

inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Compatibility

• peft>=0.10
• transformers>=4.40
• vLLM