Upload 4 files

__init__.py

@@ -0,0 +1,5 @@
+from .configuration_custom_gpt import CustomGPTConfig
+from .custom_gpt import CustomGPT
+
+CustomGPTConfig.register_for_auto_class()
+CustomGPT.register_for_auto_class("AutoModelForCausalLM")

config.json

@@ -0,0 +1,9 @@
+{
+    "block_size": 768,
+    "dropout": 0.1,
+    "model_type": "custom_gpt",
+    "n_embd": 768,
+    "n_head": 8,
+    "n_layer": 8,
+    "vocab_size": 50304
+}

configuration_gpt.py

@@ -0,0 +1,22 @@
+from dataclasses import dataclass
+from transformers import PretrainedConfig
+
+@dataclass
+class GPTConfig(PretrainedConfig):
+    """
+    Configuration class for custom GPT model.
+    """
+    model_type = "custom_gpt"
+    block_size: int = 768
+    vocab_size: int = 50257
+    n_layer: int = 8
+    n_head: int = 8
+    n_embd: int = 768
+    dropout: float = 0.1
+
+    @classmethod
+    def from_pretrained(cls, *args, **kwargs):
+        """
+        Override the from_pretrained method to handle custom configuration loading.
+        """
+        return super().from_pretrained(*args, **kwargs)

modeling_gpt.py

@@ -0,0 +1,143 @@
+import os
+import math
+import time
+import json
+import inspect
+from dataclasses import dataclass
+import torch
+import torch.nn as nn
+from torch.nn import functional as F
+from safetensors.torch import save_model
+from transformers import PreTrainedModel, PretrainedConfig, AutoConfig, AutoModelForCausalLM
+from configuration_gpt import GPTConfig
+from huggingface_hub import HfApi
+
+import os
+import json
+import torch
+from safetensors.torch import save_model
+
+
+
+# Define the CausalSelfAttention class
+class CausalSelfAttention(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        assert config.n_embd % config.n_head == 0
+        self.c_attn = nn.Linear(config.n_embd, 3 * config.n_embd)
+        self.c_proj = nn.Linear(config.n_embd, config.n_embd)
+        self.c_proj.NANOGPT_SCALE_INIT = 1
+        self.n_head = config.n_head
+        self.n_embd = config.n_embd
+
+    def forward(self, x):
+        B, T, C = x.size()
+        qkv = self.c_attn(x)
+        q, k, v = qkv.split(self.n_embd, dim=2)
+        k = k.view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
+        q = q.view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
+        v = v.view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
+        y = F.scaled_dot_product_attention(q, k, v, is_causal=True)
+        y = y.transpose(1, 2).contiguous().view(B, T, C)
+        y = self.c_proj(y)
+        return y
+
+# Define the MLP class
+class MLP(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.c_fc = nn.Linear(config.n_embd, 4 * config.n_embd)
+        self.gelu = nn.GELU(approximate='tanh')
+        self.c_proj = nn.Linear(4 * config.n_embd, config.n_embd)
+        self.c_proj.NANOGPT_SCALE_INIT = 1
+
+    def forward(self, x):
+        x = self.c_fc(x)
+        x = self.gelu(x)
+        x = self.c_proj(x)
+        return x
+
+# Define the Block class
+class Block(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.ln_1 = nn.LayerNorm(config.n_embd)
+        self.attn = CausalSelfAttention(config)
+        self.ln_2 = nn.LayerNorm(config.n_embd)
+        self.mlp = MLP(config)
+
+    def forward(self, x):
+        x = x + self.attn(self.ln_1(x))
+        x = x + self.mlp(self.ln_2(x))
+        return x
+
+# Define the GPT class
+class GPT(PreTrainedModel):
+    config_class = GPTConfig
+
+    def __init__(self, config):
+        super().__init__(config)
+        self.config = config
+        self.transformer = nn.ModuleDict(dict(
+            wte=nn.Embedding(config.vocab_size, config.n_embd),
+            wpe=nn.Embedding(config.block_size, config.n_embd),
+            h=nn.ModuleList([Block(config) for _ in range(config.n_layer)]),
+            ln_f=nn.LayerNorm(config.n_embd),
+        ))
+        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
+        self.transformer.wte.weight = self.lm_head.weight
+        self.apply(self._init_weights)
+
+    def _init_weights(self, module):
+        if isinstance(module, nn.Linear):
+            std = 0.02
+            if hasattr(module, 'NANOGPT_SCALE_INIT'):
+                std *= (2 * self.config.n_layer) ** -0.5
+            torch.nn.init.normal_(module.weight, mean=0.0, std=std)
+            if module.bias is not None:
+                torch.nn.init.zeros_(module.bias)
+        elif isinstance(module, nn.Embedding):
+            torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)
+
+    def forward(self, idx, targets=None):
+        B, T = idx.size()
+        assert T <= self.config.block_size, f"Cannot forward sequence of length {T}, block size is only {self.config.block_size}"
+        pos = torch.arange(0, T, dtype=torch.long, device=idx.device)
+        pos_emb = self.transformer.wpe(pos)
+        tok_emb = self.transformer.wte(idx)
+        x = tok_emb + pos_emb
+        for block in self.transformer.h:
+            x = block(x)
+        x = self.transformer.ln_f(x)
+        logits = self.lm_head(x)
+        loss = None
+        if targets is not None:
+            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1))
+        return logits, loss
+
+    def save_pretrained(self, save_directory):
+        super().save_pretrained(save_directory)
+        torch.save(self.state_dict(), os.path.join(save_directory, "pytorch_model.bin"))
+
+    @classmethod
+    def from_pretrained(cls, *args, **kwargs):
+        return super().from_pretrained(*args, **kwargs)
+    def push_to_hub(self, repo_id, private=False, commit_message="Push model to hub"):
+        # Save the model locally
+        self.save_pretrained(repo_id)
+        
+        # Use HfApi to push the model to the Hugging Face Hub
+        api = HfApi()
+        api.upload_folder(
+            folder_path=repo_id,
+            repo_id=repo_id,
+            repo_type="model",
+            private=private,
+            commit_message=commit_message
+        )
+
+    
+AutoConfig.register("custom_gpt", GPTConfig)
+AutoModelForCausalLM.register(GPTConfig, GPT)
+config = GPTConfig()
+model = GPT(config)