Upload 8 files

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Hebrew_GPT2_345M",
+  "_name_or_path": "Norod78/Hebrew-GPT2-345M-Stage",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -28,7 +28,7 @@
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.27.0.dev0",
+  "transformers_version": "4.41.2",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.27.0.dev0"
+  "transformers_version": "4.41.2"
 }

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2 - Trained by `huggingface/tokenizers`
+#version: 0.2
 Ġ ×
 × Ļ
 × ķ

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e1d8ecedc8fa6cad81f823d92ed697279ad3b9586fbe2ce82b0cae47351a486
-size 1444493752
+oid sha256:5aaf6ec1e396167aadd8d33d9dae19a3900c6f7a6bb249182b19da625c911b06
+size 1419322880

tokenizer.json

@@ -39,6 +39,8 @@
     "continuing_subword_prefix": "",
     "end_of_word_suffix": "",
     "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "startoftext": 0,
       "<pad>": 1,

tokenizer_config.json

@@ -1,37 +1,25 @@
 {
   "add_bos_token": false,
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "305": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": false,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
   "full_tokenizer_file": null,
   "max_len": 1024,
   "model_max_length": 1024,
-  "name_or_path": "./Hebrew_GPT2_345M-Models_tokenizer",
   "pad_token": null,
-  "special_tokens_map_file": "special_tokens_map.json",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }