RLHF model of StarCoder

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9e8676d7c37b61e40b712f7e796f2b9273321bf9d2dc46cab4640b63b83af3c
+oid sha256:b2164791914a2399a54aed9ae2e0b3a6214198a8d03664276eaf378edfeccdca
 size 656601304

special_tokens_map.json

@@ -34,13 +34,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -1,20 +1,15 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 256,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": {
     "strategy": {
-      "Fixed": 256
+      "Fixed": 32
     },
-    "direction": "Right",
+    "direction": "Left",
     "pad_to_multiple_of": null,
-    "pad_id": 49152,
+    "pad_id": 0,
     "pad_type_id": 0,
-    "pad_token": "[PAD]"
+    "pad_token": "<|endoftext|>"
   },
   "added_tokens": [
     {
@@ -187,15 +182,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 49152,
-      "content": "[PAD]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -152,14 +152,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "49152": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "additional_special_tokens": [
@@ -187,7 +179,8 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>",
   "vocab_size": 49152

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46ab18728d598e8df336a50de9eae8756e806779df4977d5db38d49239627d96
+oid sha256:1e802996ed957debf7d3bf3ff709646a6f063fe24e0a857449a3a18b03a0005b
 size 4856