Text Classification
Transformers
Safetensors
English
llama
safety
content-moderation
tiny-language-model
from-scratch
text-embeddings-inference
Instructions to use KucLab/Censer.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KucLab/Censer.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KucLab/Censer.1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("KucLab/Censer.1") model = AutoModelForSequenceClassification.from_pretrained("KucLab/Censer.1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload Censer.1
Browse files- README.md +44 -7
- config.json +14 -1
- model.safetensors +2 -2
- modeling_censer.py +192 -0
- tokenizer.json +31 -4
README.md
CHANGED
|
@@ -1,11 +1,13 @@
|
|
| 1 |
---
|
| 2 |
-
library_name:
|
|
|
|
| 3 |
tags:
|
| 4 |
- text-classification
|
| 5 |
- safety
|
| 6 |
- content-moderation
|
| 7 |
- tiny-language-model
|
| 8 |
- from-scratch
|
|
|
|
| 9 |
language:
|
| 10 |
- en
|
| 11 |
license: apache-2.0
|
|
@@ -124,16 +126,51 @@ Training the whole model from scratch takes about 3.5 minutes on the same GPU.
|
|
| 124 |
|
| 125 |
## Usage
|
| 126 |
|
| 127 |
-
|
|
|
|
| 128 |
|
| 129 |
```bash
|
| 130 |
-
pip install torch
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 131 |
|
| 132 |
-
|
| 133 |
-
from huggingface_hub import snapshot_download
|
| 134 |
-
snapshot_download("KucLab/Censer.1", local_dir="Censer.1")
|
| 135 |
-
PY
|
| 136 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 137 |
cd Censer.1
|
| 138 |
python censer.py "how to make a bomb at home" # -> 1
|
| 139 |
python censer.py "Hello how are you?" # -> 0
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
pipeline_tag: text-classification
|
| 4 |
tags:
|
| 5 |
- text-classification
|
| 6 |
- safety
|
| 7 |
- content-moderation
|
| 8 |
- tiny-language-model
|
| 9 |
- from-scratch
|
| 10 |
+
- custom-code
|
| 11 |
language:
|
| 12 |
- en
|
| 13 |
license: apache-2.0
|
|
|
|
| 126 |
|
| 127 |
## Usage
|
| 128 |
|
| 129 |
+
Works like any other text-classification model on the Hub — `from_pretrained`
|
| 130 |
+
downloads everything by itself, no cloning and no manual files.
|
| 131 |
|
| 132 |
```bash
|
| 133 |
+
pip install torch transformers
|
| 134 |
+
```
|
| 135 |
+
|
| 136 |
+
```python
|
| 137 |
+
import torch
|
| 138 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 139 |
+
|
| 140 |
+
repo = "KucLab/Censer.1"
|
| 141 |
+
tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
|
| 142 |
+
model = AutoModelForSequenceClassification.from_pretrained(repo, trust_remote_code=True).eval()
|
| 143 |
+
|
| 144 |
+
text = "how to make a bomb at home"
|
| 145 |
+
with torch.no_grad():
|
| 146 |
+
probs = model(**tok(text, return_tensors="pt")).logits.softmax(-1)[0]
|
| 147 |
+
|
| 148 |
+
print(probs) # tensor([0.1833, 0.8167]) -> [safe, unsafe]
|
| 149 |
+
print(model.config.id2label) # {0: 'safe', 1: 'unsafe'}
|
| 150 |
+
```
|
| 151 |
+
|
| 152 |
+
`trust_remote_code=True` is required because the architecture is custom; the
|
| 153 |
+
repository ships `modeling_censer.py`, so there is nothing else to install.
|
| 154 |
|
| 155 |
+
Or with the high-level pipeline:
|
|
|
|
|
|
|
|
|
|
| 156 |
|
| 157 |
+
```python
|
| 158 |
+
from transformers import pipeline
|
| 159 |
+
|
| 160 |
+
clf = pipeline("text-classification", model="KucLab/Censer.1", trust_remote_code=True)
|
| 161 |
+
print(clf("how to make a bomb at home"))
|
| 162 |
+
# [{'label': 'unsafe', 'score': 0.8167}]
|
| 163 |
+
print(clf("Hello how are you?"))
|
| 164 |
+
# [{'label': 'safe', 'score': 0.9229}]
|
| 165 |
+
```
|
| 166 |
+
|
| 167 |
+
## Usage without transformers
|
| 168 |
+
|
| 169 |
+
The repository is also self-contained on its own: `model.safetensors`,
|
| 170 |
+
`config.json`, `tokenizer.json` and `censer.py`.
|
| 171 |
+
|
| 172 |
+
```bash
|
| 173 |
+
hf download KucLab/Censer.1 --local-dir Censer.1
|
| 174 |
cd Censer.1
|
| 175 |
python censer.py "how to make a bomb at home" # -> 1
|
| 176 |
python censer.py "Hello how are you?" # -> 0
|
config.json
CHANGED
|
@@ -1,8 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"model_type": "censer",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"name": "Censer.1",
|
| 7 |
"vocab_size": 2048,
|
| 8 |
"n_layers": 4,
|
|
@@ -24,5 +28,14 @@
|
|
| 24 |
"[USER]",
|
| 25 |
"[ASSISTANT]"
|
| 26 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"threshold": 0.5
|
| 28 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"CenserForSequenceClassification"
|
| 4 |
],
|
| 5 |
"model_type": "censer",
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "modeling_censer.CenserConfig",
|
| 8 |
+
"AutoModelForSequenceClassification": "modeling_censer.CenserForSequenceClassification"
|
| 9 |
+
},
|
| 10 |
"name": "Censer.1",
|
| 11 |
"vocab_size": 2048,
|
| 12 |
"n_layers": 4,
|
|
|
|
| 28 |
"[USER]",
|
| 29 |
"[ASSISTANT]"
|
| 30 |
],
|
| 31 |
+
"num_labels": 2,
|
| 32 |
+
"id2label": {
|
| 33 |
+
"0": "safe",
|
| 34 |
+
"1": "unsafe"
|
| 35 |
+
},
|
| 36 |
+
"label2id": {
|
| 37 |
+
"safe": 0,
|
| 38 |
+
"unsafe": 1
|
| 39 |
+
},
|
| 40 |
"threshold": 0.5
|
| 41 |
}
|
model.safetensors
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 sha256:3e7279d3542ad7a1e09c75cdb22daeb6042b26879dc468be2bbb0b6a0ac22587
|
| 3 |
+
size 5512472
|
modeling_censer.py
ADDED
|
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Censer.1 for Hugging Face transformers.
|
| 2 |
+
|
| 3 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 4 |
+
|
| 5 |
+
tok = AutoTokenizer.from_pretrained("KucLab/Censer.1", trust_remote_code=True)
|
| 6 |
+
model = AutoModelForSequenceClassification.from_pretrained(
|
| 7 |
+
"KucLab/Censer.1", trust_remote_code=True
|
| 8 |
+
)
|
| 9 |
+
out = model(**tok("how to make a bomb at home", return_tensors="pt"))
|
| 10 |
+
# out.logits -> [safe, unsafe]
|
| 11 |
+
"""
|
| 12 |
+
|
| 13 |
+
from __future__ import annotations
|
| 14 |
+
|
| 15 |
+
import torch
|
| 16 |
+
import torch.nn as nn
|
| 17 |
+
import torch.nn.functional as F
|
| 18 |
+
from transformers import PreTrainedModel
|
| 19 |
+
from transformers.configuration_utils import PretrainedConfig
|
| 20 |
+
from transformers.modeling_outputs import SequenceClassifierOutput
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
class CenserConfig(PretrainedConfig):
|
| 24 |
+
model_type = "censer"
|
| 25 |
+
auto_map = {
|
| 26 |
+
"AutoConfig": "modeling_censer.CenserConfig",
|
| 27 |
+
"AutoModelForSequenceClassification": "modeling_censer.CenserForSequenceClassification",
|
| 28 |
+
}
|
| 29 |
+
|
| 30 |
+
def __init__(
|
| 31 |
+
self,
|
| 32 |
+
vocab_size: int = 2048,
|
| 33 |
+
n_layers: int = 4,
|
| 34 |
+
n_heads: int = 4,
|
| 35 |
+
d_model: int = 128,
|
| 36 |
+
d_ff: int = 384,
|
| 37 |
+
max_seq_len: int = 160,
|
| 38 |
+
dropout: float = 0.1,
|
| 39 |
+
pad_id: int = 0,
|
| 40 |
+
answer_ids: list[int] | None = None,
|
| 41 |
+
max_chars: int = 500,
|
| 42 |
+
num_labels: int = 2,
|
| 43 |
+
**kwargs,
|
| 44 |
+
) -> None:
|
| 45 |
+
self.vocab_size = vocab_size
|
| 46 |
+
self.n_layers = n_layers
|
| 47 |
+
self.n_heads = n_heads
|
| 48 |
+
self.d_model = d_model
|
| 49 |
+
self.d_ff = d_ff
|
| 50 |
+
self.max_seq_len = max_seq_len
|
| 51 |
+
self.dropout = dropout
|
| 52 |
+
self.pad_id = pad_id
|
| 53 |
+
self.answer_ids = list(answer_ids or [0, 1])
|
| 54 |
+
self.max_chars = max_chars
|
| 55 |
+
kwargs.setdefault("id2label", {0: "safe", 1: "unsafe"})
|
| 56 |
+
kwargs.setdefault("label2id", {"safe": 0, "unsafe": 1})
|
| 57 |
+
super().__init__(pad_token_id=pad_id, num_labels=num_labels, **kwargs)
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
class RMSNorm(nn.Module):
|
| 61 |
+
def __init__(self, dim: int, eps: float = 1e-5) -> None:
|
| 62 |
+
super().__init__()
|
| 63 |
+
self.eps = eps
|
| 64 |
+
self.weight = nn.Parameter(torch.ones(dim))
|
| 65 |
+
|
| 66 |
+
def forward(self, x: torch.Tensor) -> torch.Tensor:
|
| 67 |
+
dtype = x.dtype
|
| 68 |
+
x = x.float()
|
| 69 |
+
x = x * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + self.eps)
|
| 70 |
+
return x.to(dtype) * self.weight
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
def build_rope_cache(seq_len: int, head_dim: int, device, dtype, base: float = 10000.0):
|
| 74 |
+
half = head_dim // 2
|
| 75 |
+
freqs = 1.0 / (base ** (torch.arange(0, half, device=device, dtype=torch.float32) / half))
|
| 76 |
+
positions = torch.arange(seq_len, device=device, dtype=torch.float32)
|
| 77 |
+
angles = torch.outer(positions, freqs)
|
| 78 |
+
cos = torch.cat((angles.cos(), angles.cos()), dim=-1).to(dtype)[:, None, :]
|
| 79 |
+
sin = torch.cat((angles.sin(), angles.sin()), dim=-1).to(dtype)[:, None, :]
|
| 80 |
+
return cos, sin
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
def apply_rope(x: torch.Tensor, cos: torch.Tensor, sin: torch.Tensor) -> torch.Tensor:
|
| 84 |
+
seq_len = x.shape[1]
|
| 85 |
+
cos, sin = cos[:seq_len], sin[:seq_len]
|
| 86 |
+
x1, x2 = x[..., : x.shape[-1] // 2], x[..., x.shape[-1] // 2 :]
|
| 87 |
+
rotated = torch.cat((-x2, x1), dim=-1)
|
| 88 |
+
return x * cos + rotated * sin
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
class Attention(nn.Module):
|
| 92 |
+
def __init__(self, cfg: CenserConfig) -> None:
|
| 93 |
+
super().__init__()
|
| 94 |
+
self.n_heads = cfg.n_heads
|
| 95 |
+
self.head_dim = cfg.d_model // cfg.n_heads
|
| 96 |
+
self.dropout = cfg.dropout
|
| 97 |
+
self.qkv = nn.Linear(cfg.d_model, 3 * cfg.d_model, bias=False)
|
| 98 |
+
self.proj = nn.Linear(cfg.d_model, cfg.d_model, bias=False)
|
| 99 |
+
|
| 100 |
+
def forward(self, x, cos, sin, mask):
|
| 101 |
+
b, t, _ = x.shape
|
| 102 |
+
q, k, v = self.qkv(x).split(x.shape[-1], dim=-1)
|
| 103 |
+
q = q.view(b, t, self.n_heads, self.head_dim)
|
| 104 |
+
k = k.view(b, t, self.n_heads, self.head_dim)
|
| 105 |
+
v = v.view(b, t, self.n_heads, self.head_dim)
|
| 106 |
+
q, k = apply_rope(q, cos, sin), apply_rope(k, cos, sin)
|
| 107 |
+
out = F.scaled_dot_product_attention(
|
| 108 |
+
q.transpose(1, 2), k.transpose(1, 2), v.transpose(1, 2),
|
| 109 |
+
attn_mask=mask,
|
| 110 |
+
dropout_p=self.dropout if self.training else 0.0,
|
| 111 |
+
is_causal=mask is None,
|
| 112 |
+
)
|
| 113 |
+
return self.proj(out.transpose(1, 2).reshape(b, t, -1))
|
| 114 |
+
|
| 115 |
+
|
| 116 |
+
class SwiGLU(nn.Module):
|
| 117 |
+
def __init__(self, cfg: CenserConfig) -> None:
|
| 118 |
+
super().__init__()
|
| 119 |
+
self.gate = nn.Linear(cfg.d_model, cfg.d_ff, bias=False)
|
| 120 |
+
self.up = nn.Linear(cfg.d_model, cfg.d_ff, bias=False)
|
| 121 |
+
self.down = nn.Linear(cfg.d_ff, cfg.d_model, bias=False)
|
| 122 |
+
|
| 123 |
+
def forward(self, x):
|
| 124 |
+
return self.down(F.silu(self.gate(x)) * self.up(x))
|
| 125 |
+
|
| 126 |
+
|
| 127 |
+
class Block(nn.Module):
|
| 128 |
+
def __init__(self, cfg: CenserConfig) -> None:
|
| 129 |
+
super().__init__()
|
| 130 |
+
self.norm1 = RMSNorm(cfg.d_model)
|
| 131 |
+
self.attn = Attention(cfg)
|
| 132 |
+
self.norm2 = RMSNorm(cfg.d_model)
|
| 133 |
+
self.mlp = SwiGLU(cfg)
|
| 134 |
+
self.dropout = nn.Dropout(cfg.dropout)
|
| 135 |
+
|
| 136 |
+
def forward(self, x, cos, sin, mask):
|
| 137 |
+
x = x + self.dropout(self.attn(self.norm1(x), cos, sin, mask))
|
| 138 |
+
x = x + self.dropout(self.mlp(self.norm2(x)))
|
| 139 |
+
return x
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
class CenserForSequenceClassification(PreTrainedModel):
|
| 143 |
+
"""Transformer trunk plus a two-way answer head: logits [safe, unsafe]."""
|
| 144 |
+
|
| 145 |
+
config_class = CenserConfig
|
| 146 |
+
base_model_prefix = ""
|
| 147 |
+
main_input_name = "input_ids"
|
| 148 |
+
|
| 149 |
+
def __init__(self, cfg: CenserConfig) -> None:
|
| 150 |
+
super().__init__(cfg)
|
| 151 |
+
self.cfg = cfg
|
| 152 |
+
self.embed = nn.Embedding(cfg.vocab_size, cfg.d_model, padding_idx=cfg.pad_id)
|
| 153 |
+
self.blocks = nn.ModuleList([Block(cfg) for _ in range(cfg.n_layers)])
|
| 154 |
+
self.norm = RMSNorm(cfg.d_model)
|
| 155 |
+
self.lm_head = nn.Linear(cfg.d_model, cfg.vocab_size, bias=False)
|
| 156 |
+
self._rope_cache = None
|
| 157 |
+
self.post_init()
|
| 158 |
+
|
| 159 |
+
def _rope(self, device, dtype):
|
| 160 |
+
key = f"{device}|{dtype}"
|
| 161 |
+
if self._rope_cache is None or self._rope_cache[2] != key:
|
| 162 |
+
head_dim = self.cfg.d_model // self.cfg.n_heads
|
| 163 |
+
cos, sin = build_rope_cache(self.cfg.max_seq_len, head_dim, device, dtype)
|
| 164 |
+
self._rope_cache = (cos, sin, key)
|
| 165 |
+
return self._rope_cache[0], self._rope_cache[1]
|
| 166 |
+
|
| 167 |
+
def _attention_mask(self, input_ids):
|
| 168 |
+
t = input_ids.shape[1]
|
| 169 |
+
pad = input_ids != self.cfg.pad_id
|
| 170 |
+
causal = torch.ones(t, t, dtype=torch.bool, device=input_ids.device).tril()
|
| 171 |
+
return pad[:, None, None, :] & causal[None, None, :, :]
|
| 172 |
+
|
| 173 |
+
def forward(self, input_ids=None, attention_mask=None, labels=None, **kwargs):
|
| 174 |
+
if input_ids is None:
|
| 175 |
+
raise ValueError("input_ids is required")
|
| 176 |
+
cos, sin = self._rope(input_ids.device, self.embed.weight.dtype)
|
| 177 |
+
mask = self._attention_mask(input_ids)
|
| 178 |
+
x = self.embed(input_ids)
|
| 179 |
+
for block in self.blocks:
|
| 180 |
+
x = block(x, cos, sin, mask)
|
| 181 |
+
hidden = self.norm(x)
|
| 182 |
+
non_pad = (input_ids != self.cfg.pad_id).sum(dim=1).clamp(min=1)
|
| 183 |
+
idx = (non_pad - 1)[:, None, None].expand(-1, 1, hidden.shape[-1])
|
| 184 |
+
pooled = hidden.gather(1, idx)[:, 0, :]
|
| 185 |
+
logits = self.lm_head(pooled).float()
|
| 186 |
+
answer_ids = torch.tensor(self.cfg.answer_ids, device=logits.device)
|
| 187 |
+
logits = logits.index_select(-1, answer_ids)
|
| 188 |
+
|
| 189 |
+
loss = None
|
| 190 |
+
if labels is not None:
|
| 191 |
+
loss = F.cross_entropy(logits, labels.to(logits.device))
|
| 192 |
+
return SequenceClassifierOutput(logits=logits, loss=loss)
|
tokenizer.json
CHANGED
|
@@ -50,11 +50,29 @@
|
|
| 50 |
"post_processor": {
|
| 51 |
"type": "TemplateProcessing",
|
| 52 |
"single": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
{
|
| 54 |
"Sequence": {
|
| 55 |
"id": "A",
|
| 56 |
"type_id": 0
|
| 57 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
}
|
| 59 |
],
|
| 60 |
"pair": [
|
|
@@ -72,6 +90,15 @@
|
|
| 72 |
}
|
| 73 |
],
|
| 74 |
"special_tokens": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
"[BOS]": {
|
| 76 |
"id": "[BOS]",
|
| 77 |
"ids": [
|
|
@@ -81,13 +108,13 @@
|
|
| 81 |
"[BOS]"
|
| 82 |
]
|
| 83 |
},
|
| 84 |
-
"[
|
| 85 |
-
"id": "[
|
| 86 |
"ids": [
|
| 87 |
-
|
| 88 |
],
|
| 89 |
"tokens": [
|
| 90 |
-
"[
|
| 91 |
]
|
| 92 |
}
|
| 93 |
}
|
|
|
|
| 50 |
"post_processor": {
|
| 51 |
"type": "TemplateProcessing",
|
| 52 |
"single": [
|
| 53 |
+
{
|
| 54 |
+
"SpecialToken": {
|
| 55 |
+
"id": "[BOS]",
|
| 56 |
+
"type_id": 0
|
| 57 |
+
}
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"SpecialToken": {
|
| 61 |
+
"id": "[USER]",
|
| 62 |
+
"type_id": 0
|
| 63 |
+
}
|
| 64 |
+
},
|
| 65 |
{
|
| 66 |
"Sequence": {
|
| 67 |
"id": "A",
|
| 68 |
"type_id": 0
|
| 69 |
}
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"SpecialToken": {
|
| 73 |
+
"id": "[ASSISTANT]",
|
| 74 |
+
"type_id": 0
|
| 75 |
+
}
|
| 76 |
}
|
| 77 |
],
|
| 78 |
"pair": [
|
|
|
|
| 90 |
}
|
| 91 |
],
|
| 92 |
"special_tokens": {
|
| 93 |
+
"[ASSISTANT]": {
|
| 94 |
+
"id": "[ASSISTANT]",
|
| 95 |
+
"ids": [
|
| 96 |
+
3
|
| 97 |
+
],
|
| 98 |
+
"tokens": [
|
| 99 |
+
"[ASSISTANT]"
|
| 100 |
+
]
|
| 101 |
+
},
|
| 102 |
"[BOS]": {
|
| 103 |
"id": "[BOS]",
|
| 104 |
"ids": [
|
|
|
|
| 108 |
"[BOS]"
|
| 109 |
]
|
| 110 |
},
|
| 111 |
+
"[USER]": {
|
| 112 |
+
"id": "[USER]",
|
| 113 |
"ids": [
|
| 114 |
+
2
|
| 115 |
],
|
| 116 |
"tokens": [
|
| 117 |
+
"[USER]"
|
| 118 |
]
|
| 119 |
}
|
| 120 |
}
|