from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "{full_repo_name}",
    trust_remote_code=True,
    torch_dtype=torch.float16  # Use float16 for efficiency
)
tokenizer = AutoTokenizer.from_pretrained("{full_repo_name}", trust_remote_code=True)

iamgiven/Qwen2.5-1.5B-Instruct-cpp

{full_repo_name} Merged (Optimized)

Usage

iamgiven/
Qwen2.5-1.5B-Instruct-cpp