Upload folder using huggingface_hub

config.json

@@ -1,21 +1,29 @@
 {
-  "activation_function": "gelu_new",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
   "architectures": [
     "GPT2LMHeadModel"
   ],
+  "attention_dropout": 0.0,
   "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
   "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "init_std": 0.02,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
+  "layerdrop": 0.0,
   "model_type": "gpt2",
-  "n_ctx": 1024,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
   "n_layer": 12,
-  "n_positions": 1024,
+  "n_positions": 2048,
+  "pad_token_id": 1,
+  "prefix": "</s>",
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -25,14 +33,9 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.55.4",
   "use_cache": true,
-  "vocab_size": 50272
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
   "transformers_version": "4.55.4"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:166bf31ed1769d56627f9896566a25be3998b7d270f0778fccef62124ca22d86
-size 497820288
+oid sha256:a664fdf684c3597509f8f995e63c6849a62e4d71044f02be918c6e647c49b280
+size 250490416

special_tokens_map.json

@@ -1,5 +1,30 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,8 +1,17 @@
 {
+  "add_bos_token": true,
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "50256": {
-      "content": "<|endoftext|>",
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -10,11 +19,13 @@
       "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
+  "bos_token": "</s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "</s>",
+  "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "unk_token": "</s>"
 }