File size: 4,793 Bytes
2eee342
 
5dcacdd
 
 
2eee342
5dcacdd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2eee342
 
 
 
 
5dcacdd
2eee342
 
 
 
 
 
 
 
 
 
 
5dcacdd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2eee342
 
 
 
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
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
import gradio as gr

import torch
import torch.nn as nn
import torch.functional as F

n_embd = 64
dropout = 0.0
block_size = 32
vocab_size = 65
n_head = 4
n_layer = 4

class Head(nn.Module):

    def __init__(self, head_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)))

        self.dropout = nn.Dropout(dropout)

    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) 
        wei = self.dropout(wei)

        v = self.value(x)
        out = wei @ v
        return out

class MultiHeadAttention(nn.Module):

    def __init__(self, num_heads, head_size):
        super().__init__()
        self.heads = nn.ModuleList([Head(head_size) for _ in range(num_heads)])
        self.proj = nn.Linear(n_embd, n_embd)
        self.dropout = nn.Dropout(dropout)

    def forward(self, x):
        out = torch.cat([h(x) for h in self.heads], dim=-1)
        out = self.dropout(self.proj(out))
        return out

class FeedFoward(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),
            nn.Dropout(dropout),
        )

    def forward(self, x):
        return self.net(x)

class Block(nn.Module):

    def __init__(self, n_embd, n_head):
        super().__init__()
        head_size = n_embd // n_head
        self.sa = MultiHeadAttention(n_head, head_size)
        self.ffwd = FeedFoward(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

class BigramLanguageModel(nn.Module):

    def __init__(self):
        super().__init__()
        self.token_embedding_table = nn.Embedding(vocab_size, n_embd)
        self.position_embedding_table = nn.Embedding(block_size, n_embd)
        self.blocks = nn.Sequential(*[Block(n_embd, n_head=n_head) for _ in range(n_layer)])
        self.ln_f = nn.LayerNorm(n_embd) 
        self.lm_head = nn.Linear(n_embd, vocab_size)

    def forward(self, idx, targets=None):
        B, T = idx.shape

        tok_emb = self.token_embedding_table(idx) 
        pos_emb = self.position_embedding_table(torch.arange(T)) 
        x = tok_emb + pos_emb 
        x = self.blocks(x) 
        x = self.ln_f(x) 
        logits = self.lm_head(x) 

        if targets is None:
            loss = None
        else:
            B, T, C = logits.shape
            logits = logits.view(B*T, C)
            targets = targets.view(B*T)
            loss = F.cross_entropy(logits, targets)

        return logits, loss

    def generate(self, idx, max_new_tokens):
        for _ in range(max_new_tokens):

            idx_cond = idx[:, -block_size:]
            logits, loss = self(idx_cond)
            logits = logits[:, -1, :] 
            probs = F.softmax(logits, dim=-1) 
            idx_next = torch.multinomial(probs, num_samples=1) 
            idx = torch.cat((idx, idx_next), dim=1) 

        return idx


chars = "\n !$&',-.3:;?ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
itos = { i:ch for i,ch in enumerate(chars) }
stoi = { ch:i for i,ch in enumerate(chars) }

decode = lambda l: ''.join([itos[i] for i in l])
encode = lambda s: [stoi[c] for c in s]

model = BigramLanguageModel()

def respond(
    message,
    history: list[tuple[str, str]],
):
    messages = [{"role": "system", "content": "Cocaine"}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""

    input_txt = encode(message)
    context = torch.tensor(input_txt).unsqueeze(0)
    # response = decode(model.generate(context, max_new_tokens=2000)[0].tolist())

    idx = context
    for _ in range(2000):

        idx_cond = idx[:, -block_size:]
        logits = model(idx_cond).logits
        logits = logits[:, -1, :] 
        probs = F.softmax(logits, dim=-1) 
        idx_next = torch.multinomial(probs, num_samples=1) 
        idx = torch.cat((idx, idx_next), dim=1) 

        yield decode(idx_next[0].tolist())

demo = gr.ChatInterface(respond)


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