osmarks/nanogpt-experiments
1
0
Fork 0
mirror of https://github.com/osmarks/nanogpt-experiments.git synced 2024-11-11 04:19:57 +00:00
Code Issues Releases Wiki Activity

allow the prompt to compe from a file

Browse Source
This commit is contained in:
Andrej Karpathy 2023-01-25 01:12:43 +00:00
parent 21675d7755
commit e0c689cf38
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
sample.py
View File

@ -11,7 +11,7 @@ from model import GPTConfig, GPT
# ----------------------------------------------------------------------------- # -----------------------------------------------------------------------------
init_from = 'resume' # either 'resume' (from an out_dir) or a gpt2 variant (e.g. 'gpt2-xl') init_from = 'resume' # either 'resume' (from an out_dir) or a gpt2 variant (e.g. 'gpt2-xl')
out_dir = 'out' # ignored if init_from is not 'resume' out_dir = 'out' # ignored if init_from is not 'resume'
start = "\n" # or "<|endoftext|>" or whatever you like start = "\n" # or "<|endoftext|>" or etc. Can also specify a file, use as: "FILE:prompt.txt"
num_samples = 10 # number of samples to draw num_samples = 10 # number of samples to draw
max_new_tokens = 500 # number of tokens generated in each sample max_new_tokens = 500 # number of tokens generated in each sample
temperature = 0.8 # 1.0 = no change, < 1.0 = less random, > 1.0 = more random, in predictions temperature = 0.8 # 1.0 = no change, < 1.0 = less random, > 1.0 = more random, in predictions
@ -74,6 +74,9 @@ else:
decode = lambda l: enc.decode(l) decode = lambda l: enc.decode(l)
# encode the beginning of the prompt # encode the beginning of the prompt
if start.startswith('FILE:'):
with open(start[5:], 'r', encoding='utf-8') as f:
start = f.read()
start_ids = encode(start) start_ids = encode(start)
x = (torch.tensor(start_ids, dtype=torch.long, device=device)[None, ...]) x = (torch.tensor(start_ids, dtype=torch.long, device=device)[None, ...])