MLP-KTLim

/

llama-3-Korean-Bllossom-8B

like 252

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()

/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1132: FutureWarning: resume_download is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use force_download=True.
warnings.warn(
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

ValueError Traceback (most recent call last)
in <cell line: 8>()
6
7 tokenizer = AutoTokenizer.from_pretrained(model_id)
----> 8 model = AutoModelForCausalLM.from_pretrained(
9 model_id,
10 torch_dtype=torch.bfloat16,

4 frames
/usr/local/lib/python3.10/dist-packages/transformers/models/llama/configuration_llama.py in _rope_scaling_validation(self)
179
180 if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:
--> 181 raise ValueError(
182 "rope_scaling must be a dictionary with two fields, type and factor, " f"got {self.rope_scaling}"
183 )

ValueError: rope_scaling must be a dictionary with two fields, type and factor, got {'factor': 8.0, 'high_freq_factor': 4.0, 'low_freq_factor': 1.0, 'original_max_position_embeddings': 8192, 'rope_type': 'llama3'}