dahara1/

llama3-8b-amd-npu

conda activate ryzenai-transformers
<your_install_path>\RyzenAI-SW\example\transformers\setup.bat

pip install transformers==4.41.2
# Updating the Transformers library will cause the LLama 2 sample to stop working.  
# If you want to run LLama 2, revert to pip install transformers==4.34.0.  
pip install tokenizers==0.19.1
pip install -U "huggingface_hub[cli]"

huggingface-cli download dahara1/llama3-8b-amd-npu --revision main --local-dir llama3-8b-amd-npu

copy <your_install_path>\RyzenAI-SW\example\transformers\models\llama2\modeling_llama_amd.py .

# set up Runtime. see https://ryzenai.docs.amd.com/en/latest/runtime_setup.html
set XLNX_VART_FIRMWARE=<your_install_path>\voe-4.0-win_amd64\1x4.xclbin
set NUM_OF_DPU_RUNNERS=1

# save below sample script as utf8 and llama-3-test.py
python llama3-test.py

import torch
import time
import os
import psutil
import transformers
from transformers import AutoTokenizer, set_seed
import qlinear
import logging

set_seed(123)
transformers.logging.set_verbosity_error()
logging.disable(logging.CRITICAL)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
]

message_list = [
	"Who are you? ", 
	# Japanese
	"あなたの乗っている船の名前は何ですか？英語ではなく全て日本語だけを使って返事をしてください",
	# Chainese
	"你经历过的最危险的冒险是什么？请用中文回答所有问题，不要用英文。",
	# French
	"À quelle vitesse va votre bateau ? Veuillez répondre uniquement en français et non en anglais.",
	# Korean
	"당신은 그 배의 어디를 좋아합니까? 영어를 사용하지 않고 모두 한국어로 대답하십시오.",
	# German
	"Wie würde Ihr Schiffsname auf Deutsch lauten? Bitte antwortet alle auf Deutsch statt auf Englisch.", 
	# Taiwanese
	"您發現過的最令人驚奇的寶藏是什麼？請僅使用台語和繁體中文回答，不要使用英文。",
]


if __name__ == "__main__":
    p = psutil.Process()
    p.cpu_affinity([0, 1, 2, 3])
    torch.set_num_threads(4)

    tokenizer = AutoTokenizer.from_pretrained("llama3-8b-amd-npu")
    ckpt = "llama3-8b-amd-npu/pytorch_llama3_8b_w_bit_4_awq_amd.pt"
    terminators = [
        tokenizer.eos_token_id,
        tokenizer.convert_tokens_to_ids("<|eot_id|>")
    ]
    model = torch.load(ckpt)
    model.eval()
    model = model.to(torch.bfloat16)

    for n, m in model.named_modules():
        if isinstance(m, qlinear.QLinearPerGrp):
            print(f"Preparing weights of layer : {n}")
            m.device = "aie"
            m.quantize_weights()

    print("system: " + messages[0]['content'])

    for i in range(len(message_list)):
        messages.append({"role": "user",  "content": message_list[i]})
        print("user: " + message_list[i])

        input = tokenizer.apply_chat_template(
        messages,
        add_generation_prompt=True,
        return_tensors="pt",
        return_dict=True
        )

        outputs = model.generate(input['input_ids'],
		max_new_tokens=600,
    		eos_token_id=terminators,
		attention_mask=input['attention_mask'],
    		do_sample=True,
    		temperature=0.6,
    		top_p=0.9)

        response = outputs[0][input['input_ids'].shape[-1]:]
        response_message = tokenizer.decode(response, skip_special_tokens=True)
        print("assistant: " + response_message)
        messages.append({"role": "system", "content": response_message})