mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-06-15 10:17:54 +00:00
3d8d5d0d58
* feat: remove on_learn_epoch fn as not used * revert: add _on_learn_epoch fn * feat: remove NaiveStrategy * test: update train_prompts tests * fix: remove prepare_llama_tokenizer_and_embedding * test: add lora arg * feat: remove roberta support in train_prompts due to runtime errs * feat: remove deberta & roberta in rm as not used * test: remove deberta and roberta tests * feat: remove deberta and roberta models as not used * fix: remove calls to roberta * fix: remove prepare_llama_tokenizer_and_embedding * chore: update transformers version * docs: update transformers version * fix: fix actor inference * fix: fix ci * feat: change llama pad token to unk * revert: revert ddp setup_distributed * fix: change llama pad token to unk * revert: undo unnecessary changes * fix: use pip to install transformers
62 lines
2.3 KiB
Python
62 lines
2.3 KiB
Python
import argparse
|
|
|
|
import torch
|
|
from coati.models.bloom import BLOOMActor
|
|
from coati.models.generation import generate
|
|
from coati.models.gpt import GPTActor
|
|
from coati.models.opt import OPTActor
|
|
from transformers import AutoTokenizer
|
|
from transformers.models.gpt2.tokenization_gpt2 import GPT2Tokenizer
|
|
|
|
|
|
def eval(args):
|
|
# configure model
|
|
if args.model == 'gpt2':
|
|
actor = GPTActor(pretrained=args.pretrain).to(torch.cuda.current_device())
|
|
elif args.model == 'bloom':
|
|
actor = BLOOMActor(pretrained=args.pretrain).to(torch.cuda.current_device())
|
|
elif args.model == 'opt':
|
|
actor = OPTActor(pretrained=args.pretrain).to(torch.cuda.current_device())
|
|
else:
|
|
raise ValueError(f'Unsupported model "{args.model}"')
|
|
|
|
state_dict = torch.load(args.model_path)
|
|
actor.load_state_dict(state_dict)
|
|
|
|
# configure tokenizer
|
|
if args.model == 'gpt2':
|
|
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
|
|
tokenizer.pad_token = tokenizer.eos_token
|
|
elif args.model == 'bloom':
|
|
tokenizer = AutoTokenizer.from_pretrained('bigscience/bloom-560m')
|
|
tokenizer.pad_token = tokenizer.eos_token
|
|
elif args.model == 'opt':
|
|
tokenizer = AutoTokenizer.from_pretrained('facebook/opt-350m')
|
|
else:
|
|
raise ValueError(f'Unsupported model "{args.model}"')
|
|
|
|
actor.eval()
|
|
input = args.input
|
|
input_ids = tokenizer.encode(input, return_tensors='pt').to(torch.cuda.current_device())
|
|
outputs = generate(actor,
|
|
input_ids,
|
|
max_length=args.max_length,
|
|
do_sample=True,
|
|
top_k=50,
|
|
top_p=0.95,
|
|
num_return_sequences=1)
|
|
output = tokenizer.batch_decode(outputs[0], skip_special_tokens=True)
|
|
print(output)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--model', default='gpt2', choices=['gpt2', 'bloom', 'opt'])
|
|
# We suggest to use the pretrained model from HuggingFace, use pretrain to configure model
|
|
parser.add_argument('--pretrain', type=str, default=None)
|
|
parser.add_argument('--model_path', type=str, default=None)
|
|
parser.add_argument('--input', type=str, default='Question: How are you ? Answer:')
|
|
parser.add_argument('--max_length', type=int, default=100)
|
|
args = parser.parse_args()
|
|
eval(args)
|