"update"

model.py

@@ -164,7 +164,7 @@ class GPT(PreTrainedModel):
         return {"input_ids": input_ids, "past_key_values": past_key_values}
 
     @torch.no_grad()
-    def generate(self, input_ids, max_new_tokens, temperature=1.0, top_k=None):
+    def generate(self, input_ids, max_new_tokens, temperature=1.0, top_k=None, attention_mask=None):
         for _ in range(max_new_tokens):
             idx_cond = input_ids if input_ids.size(1) <= self.config.block_size else input_ids[:, -self.config.block_size:]
             out = self(idx_cond)

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}