Use FastTokenizer
Browse files- README.md +1 -2
- spiece.model +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +105 -15
README.md
CHANGED
|
@@ -12,14 +12,13 @@ This repository provides large language models trained by [SB Intuitions](https:
|
|
| 12 |
|
| 13 |
## How to use
|
| 14 |
|
| 15 |
-
Please set **use_fast=False** to use our tokenizer properly.
|
| 16 |
|
| 17 |
```python
|
| 18 |
import torch
|
| 19 |
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, set_seed
|
| 20 |
|
| 21 |
model = AutoModelForCausalLM.from_pretrained("sbintuitions/sarashina2-7b", torch_dtype=torch.bfloat16, device_map="auto")
|
| 22 |
-
tokenizer = AutoTokenizer.from_pretrained("sbintuitions/sarashina2-7b"
|
| 23 |
generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
|
| 24 |
set_seed(123)
|
| 25 |
|
|
|
|
| 12 |
|
| 13 |
## How to use
|
| 14 |
|
|
|
|
| 15 |
|
| 16 |
```python
|
| 17 |
import torch
|
| 18 |
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, set_seed
|
| 19 |
|
| 20 |
model = AutoModelForCausalLM.from_pretrained("sbintuitions/sarashina2-7b", torch_dtype=torch.bfloat16, device_map="auto")
|
| 21 |
+
tokenizer = AutoTokenizer.from_pretrained("sbintuitions/sarashina2-7b")
|
| 22 |
generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
|
| 23 |
set_seed(123)
|
| 24 |
|
spiece.model
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 sha256:7aa69ad88e8e7a8c6cb65978a4a08a34755c42e055ea755a12f5b89b804212e1
|
| 3 |
+
size 1831860
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,16 +1,106 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
{
|
| 2 |
+
"extra_ids": 0,
|
| 3 |
+
"do_lower_case": false,
|
| 4 |
+
"keep_accents": true,
|
| 5 |
+
"bos_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"unk_token": "<unk>",
|
| 8 |
+
"pad_token": "<pad>",
|
| 9 |
+
"mask_token": "<mask>",
|
| 10 |
+
"cls_token": "<cls>",
|
| 11 |
+
"sep_token": "<sep>",
|
| 12 |
+
"padding_side": "left",
|
| 13 |
+
"sp_model_kwargs": {},
|
| 14 |
+
"special_tokens_map_file": null,
|
| 15 |
+
"tokenizer_class": "T5Tokenizer",
|
| 16 |
+
"added_tokens_decoder": {
|
| 17 |
+
"7": {
|
| 18 |
+
"content": "<|system|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false,
|
| 23 |
+
"special": false
|
| 24 |
+
},
|
| 25 |
+
"8": {
|
| 26 |
+
"content": "<|assistant|>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false,
|
| 31 |
+
"special": false
|
| 32 |
+
},
|
| 33 |
+
"9": {
|
| 34 |
+
"content": "<|user|>",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false,
|
| 39 |
+
"special": false
|
| 40 |
+
},
|
| 41 |
+
"10": {
|
| 42 |
+
"content": "<|available_apis|>",
|
| 43 |
+
"lstrip": false,
|
| 44 |
+
"normalized": false,
|
| 45 |
+
"rstrip": false,
|
| 46 |
+
"single_word": false,
|
| 47 |
+
"special": false
|
| 48 |
+
},
|
| 49 |
+
"11": {
|
| 50 |
+
"content": "<|api_calls|>",
|
| 51 |
+
"lstrip": false,
|
| 52 |
+
"normalized": false,
|
| 53 |
+
"rstrip": false,
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"special": false
|
| 56 |
+
},
|
| 57 |
+
"12": {
|
| 58 |
+
"content": "<|api_results|>",
|
| 59 |
+
"lstrip": false,
|
| 60 |
+
"normalized": false,
|
| 61 |
+
"rstrip": false,
|
| 62 |
+
"single_word": false,
|
| 63 |
+
"special": false
|
| 64 |
+
},
|
| 65 |
+
"13": {
|
| 66 |
+
"content": "<|code|>",
|
| 67 |
+
"lstrip": false,
|
| 68 |
+
"normalized": false,
|
| 69 |
+
"rstrip": false,
|
| 70 |
+
"single_word": false,
|
| 71 |
+
"special": false
|
| 72 |
+
},
|
| 73 |
+
"14": {
|
| 74 |
+
"content": "<|file|>",
|
| 75 |
+
"lstrip": false,
|
| 76 |
+
"normalized": false,
|
| 77 |
+
"rstrip": false,
|
| 78 |
+
"single_word": false,
|
| 79 |
+
"special": false
|
| 80 |
+
},
|
| 81 |
+
"102397": {
|
| 82 |
+
"content": "<|prefix|>",
|
| 83 |
+
"lstrip": false,
|
| 84 |
+
"normalized": false,
|
| 85 |
+
"rstrip": false,
|
| 86 |
+
"single_word": false,
|
| 87 |
+
"special": false
|
| 88 |
+
},
|
| 89 |
+
"102398": {
|
| 90 |
+
"content": "<|suffix|>",
|
| 91 |
+
"lstrip": false,
|
| 92 |
+
"normalized": false,
|
| 93 |
+
"rstrip": false,
|
| 94 |
+
"single_word": false,
|
| 95 |
+
"special": false
|
| 96 |
+
},
|
| 97 |
+
"102399": {
|
| 98 |
+
"content": "<|middle|>",
|
| 99 |
+
"lstrip": false,
|
| 100 |
+
"normalized": false,
|
| 101 |
+
"rstrip": false,
|
| 102 |
+
"single_word": false,
|
| 103 |
+
"special": false
|
| 104 |
+
}
|
| 105 |
+
}
|
| 106 |
+
}
|