import gradio as gr
#from transformers import pipeline
from contextlib import nullcontext
import torch
import tiktoken
from model import GPTConfig, GPT
import sys

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'
#start = "\n" # or "<|endoftext|>" or etc. Can also specify a file, use as: "FILE:prompt.txt"
num_samples = 1 # number of samples to draw
max_new_tokens = 300 # number of tokens generated in each sample
temperature = 1.0 # 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
seed = 1337
device = 'cuda' # examples: 'cpu', 'cuda', 'cuda:0', 'cuda:1', etc.
dtype = 'bfloat16' if torch.cuda.is_available() and torch.cuda.is_bf16_supported() else 'float32' # 'float32' or 'bfloat16' or 'float16'
compile = True # use PyTorch 2.0 to compile the model to be faster
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
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 = ('ckpt_30000.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)

enc = tiktoken.get_encoding("gpt2")
encode = lambda s: enc.encode(s, allowed_special={"<|endoftext|>"})
decode = lambda l: enc.decode(l)

def get_response(prompt,history):
    start_ids = encode(prompt)
    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)
                #return (decode(y[0].tolist()).split('[EndOfText]')[0].split('Assistant:')[1])
                return (decode(y[0].tolist()))


demo = gr.ChatInterface(get_response,description="Ask me any Sports question",)

if __name__ == "__main__":
    demo.launch()