LLM学习笔记-4

从Hugging Face加载预训练权重

1. 因为每次训练都要有资源消耗 (GPU算力，还有时间成本），所以说及时保存模型是非常重要的。
2. 教大家如何去下载Hugging Face的模型进行生成文本
   

pip install transformers
pip install tiktoken
1
2

from importlib.metadata import version

pkgs = ["numpy", "torch", "transformers"]
for p in pkgs:
    print(f"{p} version: {version(p)}")
1
2
3
4
5

numpy version: 1.26.4
torch version: 2.1.2
transformers version: 4.39.3

from transformers import GPT2Model


# allowed model names
model_names = {
    "gpt2-small": "openai-community/gpt2",         # 124M
    "gpt2-medium": "openai-community/gpt2-medium", # 355M
    "gpt2-large": "openai-community/gpt2-large",   # 774M
    "gpt2-xl": "openai-community/gpt2-xl"          # 1558M
}

CHOOSE_MODEL = "gpt2-small"

gpt_hf = GPT2Model.from_pretrained(model_names[CHOOSE_MODEL], cache_dir="checkpoints")
gpt_hf.eval()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15

GPT2Model(
(wte): Embedding(50257, 768)
(wpe): Embedding(1024, 768)
(drop): Dropout(p=0.1, inplace=False)
(h): ModuleList(
(0-11): 12 x GPT2Block(
(ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(attn): GPT2Attention(
(c_attn): Conv1D()
(c_proj): Conv1D()
(attn_dropout): Dropout(p=0.1, inplace=False)
(resid_dropout): Dropout(p=0.1, inplace=False)
)
(ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
(mlp): GPT2MLP(
(c_fc): Conv1D()
(c_proj): Conv1D()
(act): NewGELUActivation()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
(ln_f): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
)

BASE_CONFIG = {
    "vocab_size": 50257,  # Vocabulary size
    "ctx_len": 1024,      # Context length
    "drop_rate": 0.0,     # Dropout rate
    "qkv_bias": True      # Query-key-value bias
}

model_configs = {
    "gpt2-small": {"emb_dim": 768, "n_layers": 12, "n_heads": 12},
    "gpt2-medium": {"emb_dim": 1024, "n_layers": 24, "n_heads": 16},
    "gpt2-large": {"emb_dim": 1280, "n_layers": 36, "n_heads": 20},
    "gpt2-xl": {"emb_dim": 1600, "n_layers": 48, "n_heads": 25},
}


BASE_CONFIG.update(model_configs[CHOOSE_MODEL])
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16

def assign_check(left, right):
    if left.shape != right.shape:
        raise ValueError(f"Shape mismatch. Left: {left.shape}, Right: {right.shape}")
    return torch.nn.Parameter(torch.tensor(right))
1
2
3
4

import numpy as np


def load_weights(gpt, gpt_hf):

    d = gpt_hf.state_dict()

    gpt.pos_emb.weight = assign_check(gpt.pos_emb.weight, d["wpe.weight"])
    gpt.tok_emb.weight = assign_check(gpt.tok_emb.weight, d["wte.weight"])
    
    for b in range(BASE_CONFIG["n_layers"]):
        q_w, k_w, v_w = np.split(d[f"h.{b}.attn.c_attn.weight"], 3, axis=-1)
        gpt.trf_blocks[b].att.W_query.weight = assign_check(gpt.trf_blocks[b].att.W_query.weight, q_w.T)
        gpt.trf_blocks[b].att.W_key.weight = assign_check(gpt.trf_blocks[b].att.W_key.weight, k_w.T)
        gpt.trf_blocks[b].att.W_value.weight = assign_check(gpt.trf_blocks[b].att.W_value.weight, v_w.T)
    
        q_b, k_b, v_b = np.split(d[f"h.{b}.attn.c_attn.bias"], 3, axis=-1)
        gpt.trf_blocks[b].att.W_query.bias = assign_check(gpt.trf_blocks[b].att.W_query.bias, q_b)
        gpt.trf_blocks[b].att.W_key.bias = assign_check(gpt.trf_blocks[b].att.W_key.bias, k_b)
        gpt.trf_blocks[b].att.W_value.bias = assign_check(gpt.trf_blocks[b].att.W_value.bias, v_b)
    
    
        gpt.trf_blocks[b].att.out_proj.weight = assign_check(gpt.trf_blocks[b].att.out_proj.weight, d[f"h.{b}.attn.c_proj.weight"].T)
        gpt.trf_blocks[b].att.out_proj.bias = assign_check(gpt.trf_blocks[b].att.out_proj.bias, d[f"h.{b}.attn.c_proj.bias"])
    
        gpt.trf_blocks[b].ff.layers[0].weight = assign_check(gpt.trf_blocks[b].ff.layers[0].weight, d[f"h.{b}.mlp.c_fc.weight"].T)
        gpt.trf_blocks[b].ff.layers[0].bias = assign_check(gpt.trf_blocks[b].ff.layers[0].bias, d[f"h.{b}.mlp.c_fc.bias"])
        gpt.trf_blocks[b].ff.layers[2].weight = assign_check(gpt.trf_blocks[b].ff.layers[2].weight, d[f"h.{b}.mlp.c_proj.weight"].T)
        gpt.trf_blocks[b].ff.layers[2].bias = assign_check(gpt.trf_blocks[b].ff.layers[2].bias, d[f"h.{b}.mlp.c_proj.bias"])
    
        gpt.trf_blocks[b].norm1.scale = assign_check(gpt.trf_blocks[b].norm1.scale, d[f"h.{b}.ln_1.weight"])
        gpt.trf_blocks[b].norm1.shift = assign_check(gpt.trf_blocks[b].norm1.shift, d[f"h.{b}.ln_1.bias"])
        gpt.trf_blocks[b].norm2.scale = assign_check(gpt.trf_blocks[b].norm2.scale, d[f"h.{b}.ln_2.weight"])
        gpt.trf_blocks[b].norm2.shift = assign_check(gpt.trf_blocks[b].norm2.shift, d[f"h.{b}.ln_2.bias"])
    
        gpt.final_norm.scale = assign_check(gpt.final_norm.scale, d[f"ln_f.weight"])
        gpt.final_norm.shift = assign_check(gpt.final_norm.shift, d[f"ln_f.bias"])
        gpt.out_head.weight = assign_check(gpt.out_head.weight, d["wte.weight"])
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

import tiktoken
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader

#####################################
# Chapter 2
#####################################


class GPTDatasetV1(Dataset):
    def __init__(self, txt, tokenizer, max_length, stride):
        self.tokenizer = tokenizer
        self.input_ids = []
        self.target_ids = []

        # Tokenize the entire text
        token_ids = tokenizer.encode(txt)

        # Use a sliding window to chunk the book into overlapping sequences of max_length
        for i in range(0, len(token_ids) - max_length, stride):
            input_chunk = token_ids[i:i + max_length]
            target_chunk = token_ids[i + 1: i + max_length + 1]
            self.input_ids.append(torch.tensor(input_chunk))
            self.target_ids.append(torch.tensor(target_chunk))

    def __len__(self):
        return len(self.input_ids)

    def __getitem__(self, idx):
        return self.input_ids[idx], self.target_ids[idx]


def create_dataloader_v1(txt, batch_size=4, max_length=256,
                         stride=128, shuffle=True, drop_last=True):
    # Initialize the tokenizer
    tokenizer = tiktoken.get_encoding("gpt2")

    # Create dataset
    dataset = GPTDatasetV1(txt, tokenizer, max_length, stride)

    # Create dataloader
    dataloader = DataLoader(
        dataset, batch_size=batch_size, shuffle=shuffle, drop_last=drop_last)

    return dataloader


#####################################
# Chapter 3
#####################################
class MultiHeadAttention(nn.Module):
    def __init__(self, d_in, d_out, block_size, dropout, num_heads, qkv_bias=False):
        super().__init__()
        assert d_out % num_heads == 0, "d_out must be divisible by n_heads"

        self.d_out = d_out
        self.num_heads = num_heads
        self.head_dim = d_out // num_heads  # Reduce the projection dim to match desired output dim

        self.W_query = nn.Linear(d_in, d_out, bias=qkv_bias)
        self.W_key = nn.Linear(d_in, d_out, bias=qkv_bias)
        self.W_value = nn.Linear(d_in, d_out, bias=qkv_bias)
        self.out_proj = nn.Linear(d_out, d_out)  # Linear layer to combine head outputs
        self.dropout = nn.Dropout(dropout)
        self.register_buffer('mask', torch.triu(torch.ones(block_size, block_size), diagonal=1))

    def forward(self, x):
        b, num_tokens, d_in = x.shape

        keys = self.W_key(x)  # Shape: (b, num_tokens, d_out)
        queries = self.W_query(x)
        values = self.W_value(x)

        # We implicitly split the matrix by adding a `num_heads` dimension
        # Unroll last dim: (b, num_tokens, d_out) -> (b, num_tokens, num_heads, head_dim)
        keys = keys.view(b, num_tokens, self.num_heads, self.head_dim)
        values = values.view(b, num_tokens, self.num_heads, self.head_dim)
        queries = queries.view(b, num_tokens, self.num_heads, self.head_dim)

        # Transpose: (b, num_tokens, num_heads, head_dim) -> (b, num_heads, num_tokens, head_dim)
        keys = keys.transpose(1, 2)
        queries = queries.transpose(1, 2)
        values = values.transpose(1, 2)

        # Compute scaled dot-product attention (aka self-attention) with a causal mask
        attn_scores = queries @ keys.transpose(2, 3)  # Dot product for each head

        # Original mask truncated to the number of tokens and converted to boolean
        mask_bool = self.mask.bool()[:num_tokens, :num_tokens]

        # Use the mask to fill attention scores
        attn_scores.masked_fill_(mask_bool, -torch.inf)

        attn_weights = torch.softmax(attn_scores / keys.shape[-1]**0.5, dim=-1)
        attn_weights = self.dropout(attn_weights)

        # Shape: (b, num_tokens, num_heads, head_dim)
        context_vec = (attn_weights @ values).transpose(1, 2)

        # Combine heads, where self.d_out = self.num_heads * self.head_dim
        context_vec = context_vec.reshape(b, num_tokens, self.d_out)
        context_vec = self.out_proj(context_vec)  # optional projection

        return context_vec


#####################################
# Chapter 4
#####################################
class LayerNorm(nn.Module):
    def __init__(self, emb_dim):
        super().__init__()
        self.eps = 1e-5
        self.scale = nn.Parameter(torch.ones(emb_dim))
        self.shift = nn.Parameter(torch.zeros(emb_dim))

    def forward(self, x):
        mean = x.mean(dim=-1, keepdim=True)
        var = x.var(dim=-1, keepdim=True, unbiased=False)
        norm_x = (x - mean) / torch.sqrt(var + self.eps)
        return self.scale * norm_x + self.shift


class GELU(nn.Module):
    def __init__(self):
        super().__init__()

    def forward(self, x):
        return 0.5 * x * (1 + torch.tanh(
            torch.sqrt(torch.tensor(2.0 / torch.pi)) *
            (x + 0.044715 * torch.pow(x, 3))
        ))


class FeedForward(nn.Module):
    def __init__(self, cfg):
        super().__init__()
        self.layers = nn.Sequential(
            nn.Linear(cfg["emb_dim"], 4 * cfg["emb_dim"]),
            GELU(),
            nn.Linear(4 * cfg["emb_dim"], cfg["emb_dim"]),
            nn.Dropout(cfg["drop_rate"])
        )

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


class TransformerBlock(nn.Module):
    def __init__(self, cfg):
        super().__init__()
        self.att = MultiHeadAttention(
            d_in=cfg["emb_dim"],
            d_out=cfg["emb_dim"],
            block_size=cfg["ctx_len"],
            num_heads=cfg["n_heads"],
            dropout=cfg["drop_rate"],
            qkv_bias=cfg["qkv_bias"])
        self.ff = FeedForward(cfg)
        self.norm1 = LayerNorm(cfg["emb_dim"])
        self.norm2 = LayerNorm(cfg["emb_dim"])
        self.drop_resid = nn.Dropout(cfg["drop_rate"])

    def forward(self, x):
        # Shortcut connection for attention block
        shortcut = x
        x = self.norm1(x)
        x = self.att(x)   # Shape [batch_size, num_tokens, emb_size]
        x = self.drop_resid(x)
        x = x + shortcut  # Add the original input back

        # Shortcut connection for feed-forward block
        shortcut = x
        x = self.norm2(x)
        x = self.ff(x)
        x = self.drop_resid(x)
        x = x + shortcut  # Add the original input back

        return x


class GPTModel(nn.Module):
    def __init__(self, cfg):
        super().__init__()
        self.tok_emb = nn.Embedding(cfg["vocab_size"], cfg["emb_dim"])
        self.pos_emb = nn.Embedding(cfg["ctx_len"], cfg["emb_dim"])
        self.drop_emb = nn.Dropout(cfg["drop_rate"])

        self.trf_blocks = nn.Sequential(
            *[TransformerBlock(cfg) for _ in range(cfg["n_layers"])])

        self.final_norm = LayerNorm(cfg["emb_dim"])
        self.out_head = nn.Linear(cfg["emb_dim"], cfg["vocab_size"], bias=False)

    def forward(self, in_idx):
        batch_size, seq_len = in_idx.shape
        tok_embeds = self.tok_emb(in_idx)
        pos_embeds = self.pos_emb(torch.arange(seq_len, device=in_idx.device))
        x = tok_embeds + pos_embeds  # Shape [batch_size, num_tokens, emb_size]
        x = self.drop_emb(x)
        x = self.trf_blocks(x)
        x = self.final_norm(x)
        logits = self.out_head(x)
        return logits


def generate_text_simple(model, idx, max_new_tokens, context_size):
    # idx is (B, T) array of indices in the current context
    for _ in range(max_new_tokens):

        # Crop current context if it exceeds the supported context size
        # E.g., if LLM supports only 5 tokens, and the context size is 10
        # then only the last 5 tokens are used as context
        idx_cond = idx[:, -context_size:]

        # Get the predictions
        with torch.no_grad():
            logits = model(idx_cond)

        # Focus only on the last time step
        # (batch, n_token, vocab_size) becomes (batch, vocab_size)
        logits = logits[:, -1, :]

        # Get the idx of the vocab entry with the highest logits value
        idx_next = torch.argmax(logits, dim=-1, keepdim=True)  # (batch, 1)

        # Append sampled index to the running sequence
        idx = torch.cat((idx, idx_next), dim=1)  # (batch, n_tokens+1)

    return idx


#####################################
# Chapter 5
#####################################


def text_to_token_ids(text, tokenizer):
    encoded = tokenizer.encode(text)
    encoded_tensor = torch.tensor(encoded).unsqueeze(0)  # add batch dimension
    return encoded_tensor


def token_ids_to_text(token_ids, tokenizer):
    flat = token_ids.squeeze(0)  # remove batch dimension
    return tokenizer.decode(flat.tolist())


def generate(model, idx, max_new_tokens, context_size, temperature, top_k=None):

    # For-loop is the same as before: Get logits, and only focus on last time step
    for _ in range(max_new_tokens):
        idx_cond = idx[:, -context_size:]
        with torch.no_grad():
            logits = model(idx_cond)
        logits = logits[:, -1, :]

        # New: Filter logits with top_k sampling
        if top_k is not None:
            # Keep only top_k values
            top_logits, _ = torch.topk(logits, top_k)
            min_val = top_logits[:, -1]
            logits = torch.where(logits < min_val, torch.tensor(float('-inf')).to(logits.device), logits)

        # New: Apply temperature scaling
        if temperature > 0.0:
            logits = logits / temperature

            # Apply softmax to get probabilities
            probs = torch.softmax(logits, dim=-1)  # (batch_size, context_len)

            # Sample from the distribution
            idx_next = torch.multinomial(probs, num_samples=1)  # (batch_size, 1)

        # Otherwise same as before: get idx of the vocab entry with the highest logits value
        else:
            idx_next = torch.argmax(logits, dim=-1, keepdim=True)  # (batch_size, 1)

        # Same as before: append sampled index to the running sequence
        idx = torch.cat((idx, idx_next), dim=1)  # (batch_size, num_tokens+1)

    return idx
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
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285

import torch

gpt = GPTModel(BASE_CONFIG)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
load_weights(gpt, gpt_hf)
gpt.to(device);
1
2
3
4
5
6
7
8
9

import tiktoken
# from previous_chapters import generate, text_to_token_ids, token_ids_to_text

torch.manual_seed(123)

tokenizer = tiktoken.get_encoding("gpt2")

# 此处为输入的文本
content ="Hello，My name is Lihua"

idx = text_to_token_ids(content, tokenizer).to(device)

token_ids = generate(
    model=gpt,
    idx=idx,
    max_new_tokens=30,
    context_size=BASE_CONFIG["ctx_len"],
    top_k=1,
    temperature=1.0
)

print("Input text:\n", content)
print("Output text:\n", token_ids_to_text(token_ids, tokenizer))

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24

Input text:
Hello，My name is Lihua
Output text:
Hello，My name is Lihua. I am a student at the University of California, Berkeley. I am a member of the Student Government Association. I am a member of the Student