RLHF model of StarCoder

README.md

@@ -49,5 +49,5 @@ The following hyperparameters were used during training:
 
 - Transformers 4.35.2
 - Pytorch 2.1.0+cu121
-- Datasets 2.16.1
+- Datasets 2.17.0
 - Tokenizers 0.15.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2498dd934130cab6dfef49362869c4aa4353a760645bfb0d51b4f8eeacc48caf
+oid sha256:b6ecfa625687ecbcce6ef6cf9e6699ce56d0ef0e1078eadb4c7463b3599517f3
 size 656601304

special_tokens_map.json

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

tokenizer.json

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

@@ -152,6 +152,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "49152": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
@@ -179,8 +187,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "left",
+  "pad_token": "[PAD]",
   "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 sha256:2dc9322b7a6d234418fd5eea0bd93c469cd4e6ee383d0fec25e325a499e75819
+oid sha256:634f0d73674f856a40942422ae5689c52410dc84c10e66b5a50168bf529b2eb5
 size 4536