add model

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/ColabModels/GPT2SmallTheseus/pytorch_model/",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "auto_map": {
+    "AutoModel": "modeling_gpt2.GPT2LMHeadModel"
+  },
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

modeling_gpt2.py

@@ -0,0 +1,32 @@
+from torch import nn
+
+from transformers import GPT2LMHeadModel as GPT2LMHeadModelBase
+from transformers.models.gpt2.modeling_gpt2 import GPT2Block as GPT2BlockBase
+
+
+class GPT2Block(GPT2BlockBase):
+    def forward(self, x, layer_past=None, 
+                attention_mask=None, head_mask=None, use_cache=False,
+                encoder_hidden_states=None, encoder_attention_mask=None, output_attentions=None):
+      
+        x = self.ln_1(x)
+        output_attn = self.attn(
+            x, layer_past=layer_past,
+            attention_mask=attention_mask,
+            head_mask=head_mask,
+            use_cache=use_cache)
+        
+        a = output_attn[0]
+        x = x + a
+
+        m = self.mlp(self.ln_2(x))
+        x = x + m
+
+        outputs = (x,) + output_attn[1:]
+        return outputs
+
+
+class GPT2LMHeadModel(GPT2LMHeadModelBase):
+    def __init__(self, config):
+        super().__init__(config)
+        self.transformer.h = nn.ModuleList([GPT2Block(config, layer_idx) for layer_idx in range(config.n_layer)])

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20db5c11921f7238bb88123f2b19d9dd13b7b67d7c1345ace9f30876823ed93
+size 333967901