Upload folder using huggingface_hub

README.md

@@ -0,0 +1,11 @@
+---
+library_name: pytorch
+tags:
+- text-generation
+- transformer
+- char-level
+---
+
+# Char-Level Transformer Language Model
+
+A small GPT-style character-level Transformer trained on Shakespeare text.

config.json

@@ -0,0 +1 @@
+{"vocab_size": 65, "block_size": 32, "n_embd": 64, "n_head": 4, "n_layer": 4, "dropout": 0.0}

handler.py

@@ -0,0 +1,30 @@
+import json
+import torch
+from modeling import BigramLanguageModel
+
+class EndpointHandler:
+    def __init__(self, path=""):
+        with open(f"{path}/config.json") as f:
+            self.config = json.load(f)
+
+        with open(f"{path}/vocab.json") as f:
+            self.stoi = json.load(f)
+
+        self.itos = {int(v): k for k, v in self.stoi.items()}
+
+        self.model = BigramLanguageModel(self.config)
+        self.model.load_state_dict(
+            torch.load(f"{path}/pytorch_model.bin", map_location="cpu")
+        )
+        self.model.eval()
+
+    def __call__(self, data):
+        text = data["inputs"]
+        max_new_tokens = data.get("max_new_tokens", 200)
+
+        idx = torch.tensor([[self.stoi[c] for c in text]], dtype=torch.long)
+        out = self.model.generate(idx, max_new_tokens)[0]
+
+        return {
+            "generated_text": "".join(self.itos[i.item()] for i in out)
+        }

modeling.py

@@ -0,0 +1,101 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import json
+
+class BigramLanguageModel(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.vocab_size = config["vocab_size"]
+        self.block_size = config["block_size"]
+        n_embd = config["n_embd"]
+        n_head = config["n_head"]
+        n_layer = config["n_layer"]
+
+        self.token_embedding_table = nn.Embedding(self.vocab_size, n_embd)
+        self.position_embedding_table = nn.Embedding(self.block_size, n_embd)
+
+        self.blocks = nn.Sequential(*[
+            Block(n_embd, n_head) for _ in range(n_layer)
+        ])
+        self.ln_f = nn.LayerNorm(n_embd)
+        self.lm_head = nn.Linear(n_embd, self.vocab_size)
+
+    def forward(self, idx):
+        B, T = idx.shape
+        tok_emb = self.token_embedding_table(idx)
+        pos_emb = self.position_embedding_table(torch.arange(T, device=idx.device))
+        x = tok_emb + pos_emb
+        x = self.blocks(x)
+        x = self.ln_f(x)
+        return self.lm_head(x)
+
+    @torch.no_grad()
+    def generate(self, idx, max_new_tokens):
+        for _ in range(max_new_tokens):
+            idx_cond = idx[:, -self.block_size:]
+            logits = self(idx_cond)
+            logits = logits[:, -1, :]
+            probs = F.softmax(logits, dim=-1)
+            idx_next = torch.multinomial(probs, 1)
+            idx = torch.cat([idx, idx_next], dim=1)
+        return idx
+
+
+class Head(nn.Module):
+    def __init__(self, n_embd, head_size, block_size):
+        super().__init__()
+        self.key = nn.Linear(n_embd, head_size, bias=False)
+        self.query = nn.Linear(n_embd, head_size, bias=False)
+        self.value = nn.Linear(n_embd, head_size, bias=False)
+        self.register_buffer("tril", torch.tril(torch.ones(block_size, block_size)))
+
+    def forward(self, x):
+        B, T, C = x.shape
+        k = self.key(x)
+        q = self.query(x)
+        wei = q @ k.transpose(-2, -1) * C ** -0.5
+        wei = wei.masked_fill(self.tril[:T, :T] == 0, float("-inf"))
+        wei = F.softmax(wei, dim=-1)
+        v = self.value(x)
+        return wei @ v
+
+
+class MultiHeadAttention(nn.Module):
+    def __init__(self, n_embd, n_head, block_size):
+        super().__init__()
+        head_size = n_embd // n_head
+        self.heads = nn.ModuleList([
+            Head(n_embd, head_size, block_size) for _ in range(n_head)
+        ])
+        self.proj = nn.Linear(n_embd, n_embd)
+
+    def forward(self, x):
+        return self.proj(torch.cat([h(x) for h in self.heads], dim=-1))
+
+
+class FeedForward(nn.Module):
+    def __init__(self, n_embd):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Linear(n_embd, 4 * n_embd),
+            nn.ReLU(),
+            nn.Linear(4 * n_embd, n_embd),
+        )
+
+    def forward(self, x):
+        return self.net(x)
+
+
+class Block(nn.Module):
+    def __init__(self, n_embd, n_head):
+        super().__init__()
+        self.sa = MultiHeadAttention(n_embd, n_head, block_size=32)
+        self.ffwd = FeedForward(n_embd)
+        self.ln1 = nn.LayerNorm(n_embd)
+        self.ln2 = nn.LayerNorm(n_embd)
+
+    def forward(self, x):
+        x = x + self.sa(self.ln1(x))
+        x = x + self.ffwd(self.ln2(x))
+        return x

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26a2821c37b079691dc78d9ffe3e4d3a83a832c00f1443dcb33dcd605bded3f5
+size 944859

vocab.json

@@ -0,0 +1 @@
+{"\n": 0, " ": 1, "!": 2, "$": 3, "&": 4, "'": 5, ",": 6, "-": 7, ".": 8, "3": 9, ":": 10, ";": 11, "?": 12, "A": 13, "B": 14, "C": 15, "D": 16, "E": 17, "F": 18, "G": 19, "H": 20, "I": 21, "J": 22, "K": 23, "L": 24, "M": 25, "N": 26, "O": 27, "P": 28, "Q": 29, "R": 30, "S": 31, "T": 32, "U": 33, "V": 34, "W": 35, "X": 36, "Y": 37, "Z": 38, "a": 39, "b": 40, "c": 41, "d": 42, "e": 43, "f": 44, "g": 45, "h": 46, "i": 47, "j": 48, "k": 49, "l": 50, "m": 51, "n": 52, "o": 53, "p": 54, "q": 55, "r": 56, "s": 57, "t": 58, "u": 59, "v": 60, "w": 61, "x": 62, "y": 63, "z": 64}