add tokenizer
Browse files- README.md +2 -2
- tokenizer.json +2 -2
- tokenizer_config.json +0 -6
README.md
CHANGED
|
@@ -1,15 +1,15 @@
|
|
| 1 |
---
|
| 2 |
license: bigscience-bloom-rail-1.0
|
| 3 |
-
base_model: bigscience/bloom-1b7
|
| 4 |
library_name: transformers
|
| 5 |
tags:
|
| 6 |
- bloom
|
| 7 |
- Text Generation
|
| 8 |
- Farsi
|
|
|
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: bigscience-bloom-1b7-finetune-Summarization-Persian-News
|
| 11 |
results: []
|
| 12 |
-
pipeline_tag: text-generation
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 1 |
---
|
| 2 |
license: bigscience-bloom-rail-1.0
|
|
|
|
| 3 |
library_name: transformers
|
| 4 |
tags:
|
| 5 |
- bloom
|
| 6 |
- Text Generation
|
| 7 |
- Farsi
|
| 8 |
+
base_model: bigscience/bloom-1b7
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
model-index:
|
| 11 |
- name: bigscience-bloom-1b7-finetune-Summarization-Persian-News
|
| 12 |
results: []
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c15972849c91c78dfab27e2ef0eb53b17f95c4fe81be6664f7e85c6a7fffde0e
|
| 3 |
+
size 14500499
|
tokenizer_config.json
CHANGED
|
@@ -37,15 +37,9 @@
|
|
| 37 |
"bos_token": "<s>",
|
| 38 |
"clean_up_tokenization_spaces": false,
|
| 39 |
"eos_token": "</s>",
|
| 40 |
-
"max_length": 512,
|
| 41 |
"model_max_length": 1000000000000000019884624838656,
|
| 42 |
-
"pad_to_multiple_of": null,
|
| 43 |
"pad_token": "<pad>",
|
| 44 |
-
"pad_token_type_id": 0,
|
| 45 |
"padding_side": "left",
|
| 46 |
-
"stride": 0,
|
| 47 |
"tokenizer_class": "BloomTokenizer",
|
| 48 |
-
"truncation_side": "right",
|
| 49 |
-
"truncation_strategy": "longest_first",
|
| 50 |
"unk_token": "<unk>"
|
| 51 |
}
|
|
|
|
| 37 |
"bos_token": "<s>",
|
| 38 |
"clean_up_tokenization_spaces": false,
|
| 39 |
"eos_token": "</s>",
|
|
|
|
| 40 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 41 |
"pad_token": "<pad>",
|
|
|
|
| 42 |
"padding_side": "left",
|
|
|
|
| 43 |
"tokenizer_class": "BloomTokenizer",
|
|
|
|
|
|
|
| 44 |
"unk_token": "<unk>"
|
| 45 |
}
|