update model

config.json

@@ -1,21 +1,47 @@
 {
   "activation_function": "gelu",
   "architectures": [
-    "GPT2LMHeadModel"
+    "CustomGPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": "None",
   "embd_pdrop": 0.1,
+  "embedding": {
+    "block_digit_ids": [
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9,
+      10,
+      11,
+      12,
+      13,
+      14,
+      15,
+      16,
+      17,
+      18
+    ],
+    "data_offset": 2,
+    "embedding_type": "block",
+    "fixed_pos_ntk_alpha": 1.0,
+    "fixed_pos_scaling": 0.1,
+    "fixed_pos_theta": 10000.0,
+    "padding_digit_id": 1
+  },
   "eos_token_id": "None",
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 32,
-  "n_embd": 192,
-  "n_head": 6,
+  "model_type": "custom-gpt2",
+  "n_ctx": 16,
+  "n_embd": 256,
+  "n_head": 4,
   "n_inner": null,
-  "n_layer": 6,
-  "n_positions": 32,
+  "n_layer": 8,
+  "n_positions": 16,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -26,7 +52,7 @@
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.51.3",
   "use_cache": true,
-  "vocab_size": 5
+  "vocab_size": 20
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": "None",
   "eos_token_id": "None",
-  "transformers_version": "4.50.3"
+  "transformers_version": "4.51.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c651d15716b4237f87cb9ee879d27f2ccd73145b15be04d82df1a086dc1f174b
-size 10714080
+oid sha256:a8f1c83a8248ebedb863d9aedc693fd81b69e4115df05e6a0d11dcd40f2e473b
+size 25321112