GPT2Config

tokenise+train.py

@@ -28,7 +28,19 @@ def train(ouputdir: Path, blocksize: int, vocabsize: int, num_steps: int, gpu: b
 			tok = str(files[1])
 			dat = str(files[0])
 
-	config = build_gpt2_config(vocab_size=vocabsize, max_lenght=blocksize)
+	# config = build_gpt2_config(vocab_size=vocabsize, max_lenght=blocksize)
+
+	config = GPT2Config(
+        vocab_size=vocabsize,
+        n_positions=blocksize,
+        n_ctx=blocksize,
+        resid_pdrop=0.0,
+        embd_pdrop=0.0,
+        attn_pdrop=0.0,
+        summary_first_dropout=0.0,
+        bos_token_id=0,
+        eos_token_id=0
+    )
 
 	print(config)