Upload 2 files

app.py

@@ -0,0 +1,78 @@
+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)

out-shakespeare-char/ckpt.pt

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