code

left context GPT2
2023-06-08 23:28:40 +02:00 · 2023-06-08 23:21:49 +02:00
3 changed files with 17935 additions and 9 deletions
--- a/dev-0/out.tsv
+++ b/dev-0/out.tsv
--- a/gonito.yaml
+++ b/gonito.yaml
@ -1,10 +1,3 @@
-description: trigram model
+description: GPT2
 tags:
-  - neural-network
+  - decoder-only
  - trigram
 params:
  epochs: 1
  learning-rate: 0.0001
  vocab_size: 40000
  embed_size: 300
  hidden_size: 256
--- a/test-A/out.tsv
+++ b/test-A/out.tsv
Author	SHA1	Message	Date
Adrian Charkiewicz	7f67e42f2a	code	2023-06-08 23:28:40 +02:00
Adrian Charkiewicz	13e970d70f	left context GPT2	2023-06-08 23:21:49 +02:00