Delete nano_gpt

nano_gpt/app.py

@@ -1,78 +0,0 @@
-import os
-import pickle
-from contextlib import nullcontext
-import torch
-import tiktoken
-from model import GPTConfig, GPT
-import gradio as gr
-
-def sample_from_trained_model(start="\n", init_from='resume', out_dir='out-shakespeare-char', num_samples=1, 
-                              max_new_tokens=500, temperature=0.8, top_k=200, seed=1337, device='cpu', compile=False):
-    # Set the dtype
-    dtype = 'bfloat16' if torch.cuda.is_available() and torch.cuda.is_bf16_supported() else 'float16'
-    
-    # Setup seed and device
-    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)
-
-    # Load model
-    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 data if available
-    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={""})
-        decode = lambda l: enc.decode(l)
-
-    # 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)
-    x = (torch.tensor(start_ids, dtype=torch.long, device=device)[None, ...])
-
-    # Run generation
-    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())
-
-iface = gr.Interface(fn=sample_from_trained_model, inputs="text", outputs="textbox", 
-                     title="GPT Text Generator", description="Enter a prompt to generate text.")
-
-iface.launch(share=True)

nano_gpt/out-shakespeare-char/ckpt.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b46b1b2a1b037525c9c87dbc6b7f728851c729ecb4e43f81f3f56552147ada52
-size 128986474