MLP-KTLim

/

llama-3-Korean-Bllossom-8B

like 152

아래의 예제 코드를 사용했을때,

import os
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = 'MLP-KTLim/llama-3-Korean-Bllossom-8B'

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
model.eval()

LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(145088, 4096)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaSdpaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=1024, bias=False)
          (v_proj): Linear(in_features=4096, out_features=1024, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
...
    )
    (norm): LlamaRMSNorm()
  )
  (lm_head): Linear(in_features=4096, out_features=145088, bias=False)
)

ROMPT = '''당신은 유용한 AI 어시스턴트입니다. 사용자의 질의에 대해 친절하고 정확하게 답변해야 합니다.
You are a helpful AI assistant, you'll need to answer users' queries in a friendly and accurate manner.'''
instruction = ""

messages = [
    {"role": "system", "content": f"{PROMPT}"},
    {"role": "user", "content": f"{instruction}"}
    ]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = model.generate(
    input_ids,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
    repetition_penalty = 1.1
)

print(tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_tokens=True))

다음과 같은 오류가 발생합니다.

The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Setting `pad_token_id` to `eos_token_id`:144783 for open-end generation.
The following is an example of how to use the method: