hmlee/exaone_pruned

How to Load

  import torch
  from transformers import AutoModelForCausalLM
  model = AutoModelForCausalLM.from_pretrained(
      "hmlee/exaone_pruned",
      torch_dtype=torch.bfloat16,
      trust_remote_code=True,
      device_map="auto"
  )

How to use

import torch
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct")

# Choose your prompt
prompt = "Explain who you are"  # English example
prompt = "너의 소원을 말해봐"   # 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]))