Update model files

config.json

@@ -1,55 +1,31 @@
 {
-  "_name_or_path": "EleutherAI/gpt-neo-125m",
-  "activation_function": "gelu_new",
+  "_name_or_path": "facebook/opt-125m",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
   "architectures": [
-    "GPTNeoForCausalLM"
+    "OPTForCausalLM"
   ],
-  "attention_dropout": 0,
-  "attention_layers": [
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local"
-  ],
-  "attention_types": [
-    [
-      [
-        "global",
-        "local"
-      ],
-      6
-    ]
-  ],
-  "bos_token_id": 50256,
-  "classifier_dropout": 0.1,
-  "embed_dropout": 0,
-  "eos_token_id": 50256,
-  "gradient_checkpointing": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
   "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": null,
-  "layer_norm_epsilon": 1e-05,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
   "max_position_embeddings": 2048,
-  "model_type": "gpt_neo",
-  "num_heads": 12,
-  "num_layers": 12,
-  "resid_dropout": 0,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
+  "model_type": "opt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "prefix": "</s>",
   "torch_dtype": "float32",
   "transformers_version": "4.35.0",
   "use_cache": true,
-  "vocab_size": 50257,
-  "window_size": 256
+  "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": "4.35.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94f1d79e183be81d7489fa454343510f66fce176fed6a4f8dc1b8912fde2322a
-size 500811336
+oid sha256:b3a67b42504e0c101c739fe6ef0d57eb3a9ed90267e41aba8019149a472ceae1
+size 500979600

special_tokens_map.json

@@ -1,20 +1,27 @@
 {
   "bos_token": {
-    "content": "<|endoftext|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "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": "<|endoftext|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,

tokenizer_config.json

@@ -1,9 +1,17 @@
 {
-  "add_bos_token": false,
+  "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,
@@ -11,12 +19,12 @@
       "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
+  "bos_token": "</s>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "</s>",
   "errors": "replace",
-  "model_max_length": 2048,
-  "pad_token": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "unk_token": "</s>"
 }