Spaces:
Paused
Paused
File size: 2,732 Bytes
9e03479 e90d33c 4c6dd99 e90b9d0 b503ddc 9e03479 e90d33c 9e03479 e90d33c 13498f3 fdbe694 e90d33c 645214e e90d33c 645214e e90d33c 9e03479 |
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 78 |
import gradio as gr
from model import GPTConfig, GPT
import torch
from contextlib import nullcontext
import os
import pickle
def remove_caseifer(text):
new_text = ""
i = 0
while i < len(text):
if text[i] == "^":
if i+1 < len(text):
new_text += text[i+1].upper()
i += 1
else:
pass # skip this index
else:
new_text += text[i]
i += 1
return new_text
def add_caseifer(text):
new_text = ""
for char in text:
if char.isupper():
new_text += "^" + char.lower()
else:
new_text += char
return new_text
max_new_tokens = 175 # number of tokens generated in each sample
temperature = 0.8 # 1.0 = no change, < 1.0 = less random, > 1.0 = more random, in predictions
top_k = 200 # retain only the top_k most likely tokens, clamp others to have 0 probability
device = 'cpu' # examples: 'cpu', 'cuda', 'cuda:0', 'cuda:1', etc.
dtype = 'bfloat16' # 'float32' or 'bfloat16' or 'float16'
out_dir = 'model' # ignored if init_from is not 'resume'
torch.backends.cuda.matmul.allow_tf32 = True # allow tf32 on matmul
torch.backends.cudnn.allow_tf32 = True # allow tf32 on cudnn
device_type = 'cuda' if 'cuda' in device else 'cpu' # for later use in torch.autocast
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)
# init from a model saved in a specific directory
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)
meta_path = os.path.join(out_dir, 'meta.pkl')
load_meta = os.path.exists(meta_path)
with open(meta_path, 'rb') as f:
meta = pickle.load(f)
# TODO want to make this more general to arbitrary encoder/decoder schemes
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])
def gen(input):
start_ids = encode(add_caseifer(input))
x = (torch.tensor(start_ids, dtype=torch.long, device=device)[None, ...])
y = model.generate(x, max_new_tokens, temperature=temperature, top_k=top_k)
return remove_caseifer(decode(y[0].tolist()))
iface = gr.Interface(fn=gen, inputs="text", outputs="text")
iface.launch() |