merged model
Browse files- tokenizer.json +1 -6
- tokenizer_config.json +0 -2
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 1024,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_eos_token": true,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"50256": {
|
|
@@ -318,7 +317,6 @@
|
|
| 318 |
"bos_token": "<|endoftext|>",
|
| 319 |
"clean_up_tokenization_spaces": true,
|
| 320 |
"eos_token": "<|endoftext|>",
|
| 321 |
-
"max_length": 250,
|
| 322 |
"model_max_length": 2048,
|
| 323 |
"pad_token": "<|endoftext|>",
|
| 324 |
"tokenizer_class": "CodeGenTokenizer",
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"50256": {
|
|
|
|
| 317 |
"bos_token": "<|endoftext|>",
|
| 318 |
"clean_up_tokenization_spaces": true,
|
| 319 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 320 |
"model_max_length": 2048,
|
| 321 |
"pad_token": "<|endoftext|>",
|
| 322 |
"tokenizer_class": "CodeGenTokenizer",
|