Upload Codet5 small baseline
Browse files- config.json +3 -2
- generation_config.json +2 -4
- metadata.json +1 -0
- pytorch_model.bin +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -5
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"T5ForConditionalGeneration"
|
| 4 |
],
|
|
@@ -9,7 +10,6 @@
|
|
| 9 |
"decoder_start_token_id": 0,
|
| 10 |
"dense_act_fn": "gelu_new",
|
| 11 |
"dropout_rate": 0.1,
|
| 12 |
-
"dtype": "float32",
|
| 13 |
"eos_token_id": 1,
|
| 14 |
"feed_forward_proj": "gated-gelu",
|
| 15 |
"gradient_checkpointing": false,
|
|
@@ -26,7 +26,8 @@
|
|
| 26 |
"relative_attention_max_distance": 128,
|
| 27 |
"relative_attention_num_buckets": 32,
|
| 28 |
"tie_word_embeddings": false,
|
| 29 |
-
"
|
|
|
|
| 30 |
"use_cache": true,
|
| 31 |
"vocab_size": 32100
|
| 32 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/home/jcole75/arc_our_submissions_and_related_experiments/code_small_2024-11-19",
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
|
|
|
| 10 |
"decoder_start_token_id": 0,
|
| 11 |
"dense_act_fn": "gelu_new",
|
| 12 |
"dropout_rate": 0.1,
|
|
|
|
| 13 |
"eos_token_id": 1,
|
| 14 |
"feed_forward_proj": "gated-gelu",
|
| 15 |
"gradient_checkpointing": false,
|
|
|
|
| 26 |
"relative_attention_max_distance": 128,
|
| 27 |
"relative_attention_num_buckets": 32,
|
| 28 |
"tie_word_embeddings": false,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.38.2",
|
| 31 |
"use_cache": true,
|
| 32 |
"vocab_size": 32100
|
| 33 |
}
|
generation_config.json
CHANGED
|
@@ -1,9 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"decoder_start_token_id": 0,
|
| 4 |
-
"eos_token_id":
|
| 5 |
-
1
|
| 6 |
-
],
|
| 7 |
"pad_token_id": 0,
|
| 8 |
-
"transformers_version": "4.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
|
|
|
|
|
|
| 5 |
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.38.2"
|
| 7 |
}
|
metadata.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"title": "ARC CodeT5 Small", "id": "jcole75/codet5-small", "licenses": [{"name": "CC0-1.0"}]}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65141266cb80ce67ee94853e264ab646e8a1e5341390a7ed16346110b595974f
|
| 3 |
+
size 307792773
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": null,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
"content": "<pad>",
|
|
@@ -928,12 +927,9 @@
|
|
| 928 |
"<extra_id_98>",
|
| 929 |
"<extra_id_99>"
|
| 930 |
],
|
| 931 |
-
"alpha": 0.2,
|
| 932 |
"clean_up_tokenization_spaces": true,
|
| 933 |
-
"enable_sampling": true,
|
| 934 |
"eos_token": "</s>",
|
| 935 |
"extra_ids": 100,
|
| 936 |
-
"extra_special_tokens": {},
|
| 937 |
"max_length": 500,
|
| 938 |
"model_max_length": 1000000000000000019884624838656,
|
| 939 |
"pad_to_multiple_of": null,
|
|
@@ -941,7 +937,7 @@
|
|
| 941 |
"pad_token_type_id": 0,
|
| 942 |
"padding_side": "right",
|
| 943 |
"stride": 0,
|
| 944 |
-
"tokenizer_class": "
|
| 945 |
"truncation_side": "right",
|
| 946 |
"truncation_strategy": "longest_first",
|
| 947 |
"unk_token": "<unk>"
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<pad>",
|
|
|
|
| 927 |
"<extra_id_98>",
|
| 928 |
"<extra_id_99>"
|
| 929 |
],
|
|
|
|
| 930 |
"clean_up_tokenization_spaces": true,
|
|
|
|
| 931 |
"eos_token": "</s>",
|
| 932 |
"extra_ids": 100,
|
|
|
|
| 933 |
"max_length": 500,
|
| 934 |
"model_max_length": 1000000000000000019884624838656,
|
| 935 |
"pad_to_multiple_of": null,
|
|
|
|
| 937 |
"pad_token_type_id": 0,
|
| 938 |
"padding_side": "right",
|
| 939 |
"stride": 0,
|
| 940 |
+
"tokenizer_class": "T5Tokenizer",
|
| 941 |
"truncation_side": "right",
|
| 942 |
"truncation_strategy": "longest_first",
|
| 943 |
"unk_token": "<unk>"
|