Upload folder using huggingface_hub

config.json

@@ -1,55 +1,39 @@
 {
-  "_name_or_path": "EleutherAI/gpt-neo-125M",
+  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
-    "GPTNeoForCausalLM"
-  ],
-  "attention_dropout": 0,
-  "attention_layers": [
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local"
-  ],
-  "attention_types": [
-    [
-      [
-        "global",
-        "local"
-      ],
-      6
-    ]
+    "GPT2LMHeadModel"
   ],
+  "attn_pdrop": 0.1,
   "bos_token_id": 50256,
-  "classifier_dropout": 0.1,
-  "embed_dropout": 0,
+  "embd_pdrop": 0.1,
   "eos_token_id": 50256,
-  "gradient_checkpointing": false,
-  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": null,
   "layer_norm_epsilon": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "gpt_neo",
-  "num_heads": 12,
-  "num_layers": 12,
-  "resid_dropout": 0,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.46.3",
   "use_cache": true,
-  "vocab_size": 50257,
-  "window_size": 256
+  "vocab_size": 50257
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27c049d05b3c1c6bddb1fa2657e01fa4ada43be88573ef660c2503e8d6c81c43
-size 500811336
+oid sha256:31cbf7d7a629bfaed724bfd6ec69dbfa161e3dc8a7b27362bf866976889b20ef
+size 497774208

special_tokens_map.json

@@ -1,24 +1,6 @@
 {
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
   "pad_token": "<|endoftext|>",
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -1,5 +1,4 @@
 {
-  "add_bos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "50256": {
@@ -12,10 +11,9 @@
     }
   },
   "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "model_max_length": 2048,
+  "model_max_length": 1024,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4c666ebe9ca6ef8728385a3d3333c19c27e0a5ded14defdd850b5af2faae7ee
+oid sha256:813062ba8003f1b08fe674315d9f8b4a9929c631d53749d8e4d1bc9b3599ca40
 size 5240