RLHF model of StarCoder

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2164791914a2399a54aed9ae2e0b3a6214198a8d03664276eaf378edfeccdca
+oid sha256:7238b285b314e21148702302531cde42d2b900153ce19a27e7a7aeac87e5fe6b
 size 656601304

special_tokens_map.json

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

tokenizer.json

@@ -1,9 +1,14 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 256,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": {
     "strategy": {
-      "Fixed": 32
+      "Fixed": 256
     },
     "direction": "Left",
     "pad_to_multiple_of": null,

tokenizer_config.json

@@ -178,8 +178,11 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "max_length": 32,
   "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
   "padding_side": "left",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>",

training_args.bin

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