llama v2 model

hugging face

llama 실행해 보기

import torch
from transformers import LlamaTokenizer, LlamaForCausalLM

## v2 models
model_path = 'openlm-research/open_llama_7b_v2'

## v1 models
# model_path = 'openlm-research/open_llama_3b'
# model_path = 'openlm-research/open_llama_7b'
# model_path = 'openlm-research/open_llama_13b'

tokenizer = LlamaTokenizer.from_pretrained(model_path)
model = LlamaForCausalLM.from_pretrained(
    model_path, torch_dtype=torch.float16, device_map='auto',
)

prompt = 'Q: What is the largest animal?\nA:'
input_ids = tokenizer(prompt, return_tensors="pt").input_ids

generation_output = model.generate(
    input_ids=input_ids, max_new_tokens=32
)
print(tokenizer.decode(generation_output[0]))

실행결과… 일단 뭐좀 더 깔아라.. ㅜㅜ …

install

pip install sentencepiece

기본 질문을 변경해서 질문하면 답변을 해준다.

그럼 지속적으로 질문할수 이는 코드로 변경해 보자. 아래 코드는 조금 더 수정을 해야 할듯.. ㅡㅡ;

import torch
from transformers import LlamaTokenizer, LlamaForCausalLM

## v2 models
model_path = 'openlm-research/open_llama_7b_v2'

## v1 models
# model_path = 'openlm-research/open_llama_3b'
# model_path = 'openlm-research/open_llama_7b'
# model_path = 'openlm-research/open_llama_13b'

tokenizer = LlamaTokenizer.from_pretrained(model_path)
model = LlamaForCausalLM.from_pretrained(
        model_path, torch_dtype=torch.float16, device_map='auto',

)

while True:
    #prompt = 'Q: What is the largest city?\nA:'
    prompt = input("Ask a question:")
    prompt = "Q: "+ prompt + "?\nA:"
    print(prompt)
    input_ids = tokenizer(prompt, return_tensors="pt").input_ids

    generation_output = model.generate(
            input_ids=input_ids, max_new_tokens=32

    )
    print(tokenizer.decode(generation_output[0]))