metadata
language:
- ko
- en
base_model:
- LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct
How to Load
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "hmlee/exaone_prune_sftv4_int4"
model = AutoModelForCausalLM.from_pretrained(
model_path,
torch_dtype="auto"
trust_remote_code=True,
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_path)
How to use
# Choose your prompt
prompt = "Explain who you are" # English example
prompt = "๋์ ์์์ ๋งํด๋ด" # Korean example
messages = [
{"role": "system",
"content": "You are EXAONE model from LG AI Research, a helpful assistant."},
{"role": "user", "content": prompt}
]
input_ids = tokenizer.apply_chat_template(
messages,
tokenize=True,
add_generation_prompt=True,
return_tensors="pt"
)
output = model.generate(
input_ids.to(model.device),
eos_token_id=tokenizer.eos_token_id,
max_new_tokens=128
)
print(tokenizer.decode(output[0]))