mirror of
https://github.com/osmarks/nanogpt-experiments.git
synced 2024-11-14 05:44:51 +00:00
56 lines
1.9 KiB
Python
56 lines
1.9 KiB
Python
"""
|
|
Sample from a trained model
|
|
"""
|
|
import os
|
|
import torch
|
|
import tiktoken
|
|
from model import GPTConfig, GPT
|
|
|
|
# -----------------------------------------------------------------------------
|
|
out_dir = 'out'
|
|
device = 'cuda'
|
|
compile = False
|
|
start = "\n" # or "<|endoftext|>" or whatever you like
|
|
num_samples = 10 # number of samples to draw
|
|
max_new_tokens = 500 # number of tokens generated in each sample
|
|
temperature = 0.8 # higher temperature (up to 1) is more random, lower (down to 0) means more greedy
|
|
top_k = 200 # retain only the top_k most likely tokens, clamp others to have 0 probability
|
|
seed = 1337
|
|
exec(open('configurator.py').read()) # overrides from command line or config file
|
|
# -----------------------------------------------------------------------------
|
|
|
|
torch.manual_seed(seed)
|
|
torch.cuda.manual_seed(seed)
|
|
torch.backends.cuda.matmul.allow_tf32 = True # allow tf32 on matmul
|
|
torch.backends.cudnn.allow_tf32 = True # allow tf32 on cudnn
|
|
|
|
# model
|
|
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)
|
|
model.eval()
|
|
model.to(device)
|
|
if compile:
|
|
model = torch.compile(model) # requires PyTorch 2.0 (optional)
|
|
|
|
# encode the beginning of the prompt
|
|
enc = tiktoken.get_encoding("gpt2")
|
|
start_ids = enc.encode(start, allowed_special={"<|endoftext|>"})
|
|
x = (torch.tensor(start_ids, dtype=torch.long, device=device)[None, ...])
|
|
|
|
for k in range(num_samples):
|
|
|
|
with torch.no_grad():
|
|
with torch.amp.autocast(device_type="cuda", dtype=torch.bfloat16):
|
|
y = model.generate(x, max_new_tokens, temperature=temperature, top_k=top_k)
|
|
|
|
print(enc.decode(y[0].tolist()))
|
|
print('---------------')
|