File size: 2,631 Bytes
8d7a40a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 |
import os
import pickle
from contextlib import nullcontext
import torch
import tiktoken
from model import GPTConfig, GPT
init_from = 'resume'
out_dir = 'out'
start = "\n"
num_samples = 10
max_new_tokens = 500
temperature = 0.8
top_k = 200
seed = 1337
device = 'cuda'
dtype = 'bfloat16' if torch.cuda.is_available() and torch.cuda.is_bf16_supported() else 'float16'
compile = False
exec(open('configurator.py').read())
torch.manual_seed(seed)
torch.cuda.manual_seed(seed)
torch.backends.cuda.matmul.allow_tf32 = True
torch.backends.cudnn.allow_tf32 = True
device_type = 'cuda' if 'cuda' in device else 'cpu'
ptdtype = {'float32': torch.float32, 'bfloat16': torch.bfloat16, 'float16': torch.float16}[dtype]
ctx = nullcontext() if device_type == 'cpu' else torch.amp.autocast(device_type=device_type, dtype=ptdtype)
if init_from == 'resume':
ckpt_path = os.path.join(out_dir, 'ckpt.pt')
checkpoint = torch.load(ckpt_path, map_location=device)
gptconf = GPTConfig(**checkpoint['model_args'])
model = GPT(gptconf)
state_dict = checkpoint['model']
unwanted_prefix = '_orig_mod.'
for k,v in list(state_dict.items()):
if k.startswith(unwanted_prefix):
state_dict[k[len(unwanted_prefix):]] = state_dict.pop(k)
model.load_state_dict(state_dict)
elif init_from.startswith('gpt2'):
model = GPT.from_pretrained(init_from, dict(dropout=0.0))
model.eval()
model.to(device)
if compile:
model = torch.compile(model)
load_meta = False
if init_from == 'resume' and 'config' in checkpoint and 'dataset' in checkpoint['config']:
meta_path = os.path.join('data', checkpoint['config']['dataset'], 'meta.pkl')
load_meta = os.path.exists(meta_path)
if load_meta:
print(f"Loading meta from {meta_path}...")
with open(meta_path, 'rb') as f:
meta = pickle.load(f)
stoi, itos = meta['stoi'], meta['itos']
encode = lambda s: [stoi[c] for c in s]
decode = lambda l: ''.join([itos[i] for i in l])
else:
print("No meta.pkl found, assuming GPT-2 encodings...")
enc = tiktoken.get_encoding("gpt2")
encode = lambda s: enc.encode(s, allowed_special={"<|endoftext|>"})
decode = lambda l: enc.decode(l)
if start.startswith('FILE:'):
with open(start[5:], 'r', encoding='utf-8') as f:
start = f.read()
start_ids = encode(start)
x = (torch.tensor(start_ids, dtype=torch.long, device=device)[None, ...])
with torch.no_grad():
with ctx:
for k in range(num_samples):
y = model.generate(x, max_new_tokens, temperature=temperature, top_k=top_k)
print(decode(y[0].tolist()))
print('---------------')
|