From 33d0fda2a22d6e7cdf5ef84a7be92e6a2782bdf0 Mon Sep 17 00:00:00 2001
From: gauthiier <d@gauthiier.info>
Date: Thu, 10 Feb 2022 14:38:39 +0100
Subject: [PATCH] revert demo

---
 tokenise+train.py | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)

diff --git a/tokenise+train.py b/tokenise+train.py
index 4c24966..35b227f 100644
--- a/tokenise+train.py
+++ b/tokenise+train.py
@@ -28,19 +28,24 @@ def train(filepath: str, ouputdir: Path, blocksize: int, vocabsize: int, num_ste
 	else:
 		return "No valid tokenizer in " + str(ouputdir)
 
-	config = build_gpt2_config(vocab_size=vocabsize, max_lenght=blocksize, dropout=0.0, n_embd=256, n_layer=8, n_head=8)
+	# config = build_gpt2_config(vocab_size=vocabsize, max_lenght=blocksize, dropout=0.0, n_embd=256, n_layer=8, n_head=8)
 
-# 	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
- #    )
+	config = GPT2Config(
+        vocab_size=vocabsize,
+        max_lenght=blocksize,
+        n_positions=blocksize,
+        n_ctx=blocksize,
+        n_embd=256,
+        n_layer=8,
+        n_head=8,
+        dropout=0.0,
+        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)