RLHF model of StarCoder

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2161f54615a151b951ae7fda67f2899cf215f32e610ed6b409a2727507f63142
+oid sha256:2498dd934130cab6dfef49362869c4aa4353a760645bfb0d51b4f8eeacc48caf
 size 656601304

special_tokens_map.json

@@ -22,12 +22,6 @@
   ],
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "<|endoftext|>",
   "unk_token": "<|endoftext|>"
 }

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 sha256:634f0d73674f856a40942422ae5689c52410dc84c10e66b5a50168bf529b2eb5
+oid sha256:2dc9322b7a6d234418fd5eea0bd93c469cd4e6ee383d0fec25e325a499e75819
 size 4536