Text Classification
Transformers
Safetensors
Telugu
chandassu_poem_cnn
feature-extraction
telugu
poetry
poetic-meter
cnn
eight-class
custom_code
Instructions to use sprx7767/chandassu-recognition with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sprx7767/chandassu-recognition with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="sprx7767/chandassu-recognition", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("sprx7767/chandassu-recognition", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
feat: enable CNN Auto loading
Browse files- cnn/README.md +10 -28
- cnn/config.json +23 -0
- cnn/hf_model.py +176 -0
- cnn/manifest.json +3 -1
- cnn/tokenizer_config.json +11 -0
cnn/README.md
CHANGED
|
@@ -1,36 +1,18 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
license: other
|
| 3 |
license_name: chandassu-citation
|
| 4 |
license_link: LICENSE
|
| 5 |
-
|
| 6 |
-
tags: [telugu, poetry, metre, cnn]
|
| 7 |
-
library_name: pytorch
|
| 8 |
pipeline_tag: text-classification
|
|
|
|
| 9 |
---
|
| 10 |
# Chandassu CNN
|
| 11 |
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
`inference.py --model_dir PATH`. This custom encoder/head package does not implement
|
| 20 |
-
the generic Transformers AutoModel interface. No pickle is required for inference.
|
| 21 |
-
|
| 22 |
-
Training: 6,517 poems; separate calibration: 908; selection: 1,859.
|
| 23 |
-
Historical diagnostic: 2,234 poems, already inspected during earlier project development.
|
| 24 |
-
See metadata.json and the repository results/v1 for full metrics and provenance.
|
| 25 |
-
This is a restricted classifier: it cannot reliably reject other metres or provide
|
| 26 |
-
prosodic explanations. Scores are calibrated probabilities, not confidence intervals.
|
| 27 |
-
Source edition/transcription rights are not independently cleared; dataset terms
|
| 28 |
-
retain their source terms. See the repository data/LICENSE.md.
|
| 29 |
-
Project-owned material uses the citation terms in LICENSE. Earlier Apache-2.0 permissions remain in effect.
|
| 30 |
-
|
| 31 |
-
## Citation
|
| 32 |
-
|
| 33 |
-
Pranav Surampudi (2026). Chandassu Recognition: Telugu Poetic Meter Classification.
|
| 34 |
-
https://github.com/Pranav-20186017/chandassu_recognition
|
| 35 |
-
|
| 36 |
-
See CITATION.cff for citation metadata and LICENSE for the applicable terms.
|
|
|
|
| 1 |
---
|
| 2 |
+
language: te
|
| 3 |
license: other
|
| 4 |
license_name: chandassu-citation
|
| 5 |
license_link: LICENSE
|
| 6 |
+
library_name: transformers
|
|
|
|
|
|
|
| 7 |
pipeline_tag: text-classification
|
| 8 |
+
tags: [telugu, poetry, metre, cnn]
|
| 9 |
---
|
| 10 |
# Chandassu CNN
|
| 11 |
|
| 12 |
+
Use `AutoTokenizer` and `AutoModelForSequenceClassification` with
|
| 13 |
+
`subfolder="cnn"` and `trust_remote_code=True`.
|
| 14 |
+
The model returns raw logits for each line. Divide logits by `model.config.calibration_temperature`
|
| 15 |
+
before applying softmax. For a four-line poem, average the four probability vectors.
|
| 16 |
+
See the [main model card](https://huggingface.co/sprx7767/chandassu-recognition)
|
| 17 |
+
for code, results, limits, and citation terms.
|
| 18 |
+
The project loader and `inference.py` also support this package.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cnn/config.json
CHANGED
|
@@ -1,7 +1,16 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
| 2 |
"artifact_schema": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"base_model": "google/byt5-small",
|
| 4 |
"calibration_fraction": 0.15,
|
|
|
|
| 5 |
"cpu_threads": 4,
|
| 6 |
"data_dir": "data/v1",
|
| 7 |
"device": "auto",
|
|
@@ -13,12 +22,24 @@
|
|
| 13 |
"folds": 3,
|
| 14 |
"gradient_checkpointing": false,
|
| 15 |
"gradient_clip": 1.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"init_checkpoint": null,
|
| 17 |
"kernel_sizes": [
|
| 18 |
3,
|
| 19 |
5,
|
| 20 |
7
|
| 21 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
"labels": [
|
| 23 |
"ఉత్పలమాల",
|
| 24 |
"చంపకమాల",
|
|
@@ -37,6 +58,7 @@
|
|
| 37 |
"model_revision": "68377bdc18a2ffec8a0533fef03b1c513a4dd49d",
|
| 38 |
"model_type": "cnn",
|
| 39 |
"output_dir": "runs/cnn-seed-17",
|
|
|
|
| 40 |
"patience": 12,
|
| 41 |
"precision": "auto",
|
| 42 |
"progress_every": 50,
|
|
@@ -46,6 +68,7 @@
|
|
| 46 |
"split_manifest": "splits/final_h100.json",
|
| 47 |
"split_seed": 142,
|
| 48 |
"temperature": 1.34592281013039,
|
|
|
|
| 49 |
"weight_decay": 0.01,
|
| 50 |
"width": 64
|
| 51 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ChandassuCNNForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
"artifact_schema": 1,
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "hf_model.ChandassuCNNConfig",
|
| 8 |
+
"AutoModel": "hf_model.ChandassuCNNForSequenceClassification",
|
| 9 |
+
"AutoModelForSequenceClassification": "hf_model.ChandassuCNNForSequenceClassification"
|
| 10 |
+
},
|
| 11 |
"base_model": "google/byt5-small",
|
| 12 |
"calibration_fraction": 0.15,
|
| 13 |
+
"calibration_temperature": 1.34592281013039,
|
| 14 |
"cpu_threads": 4,
|
| 15 |
"data_dir": "data/v1",
|
| 16 |
"device": "auto",
|
|
|
|
| 22 |
"folds": 3,
|
| 23 |
"gradient_checkpointing": false,
|
| 24 |
"gradient_clip": 1.0,
|
| 25 |
+
"id2label": {
|
| 26 |
+
"0": "ఉత్పలమాల",
|
| 27 |
+
"1": "చంపకమాల",
|
| 28 |
+
"2": "మత్తేభము",
|
| 29 |
+
"3": "శార్దూలం"
|
| 30 |
+
},
|
| 31 |
"init_checkpoint": null,
|
| 32 |
"kernel_sizes": [
|
| 33 |
3,
|
| 34 |
5,
|
| 35 |
7
|
| 36 |
],
|
| 37 |
+
"label2id": {
|
| 38 |
+
"ఉత్పలమాల": 0,
|
| 39 |
+
"చంపకమాల": 1,
|
| 40 |
+
"మత్తేభము": 2,
|
| 41 |
+
"శార్దూలం": 3
|
| 42 |
+
},
|
| 43 |
"labels": [
|
| 44 |
"ఉత్పలమాల",
|
| 45 |
"చంపకమాల",
|
|
|
|
| 58 |
"model_revision": "68377bdc18a2ffec8a0533fef03b1c513a4dd49d",
|
| 59 |
"model_type": "cnn",
|
| 60 |
"output_dir": "runs/cnn-seed-17",
|
| 61 |
+
"pad_token_id": 0,
|
| 62 |
"patience": 12,
|
| 63 |
"precision": "auto",
|
| 64 |
"progress_every": 50,
|
|
|
|
| 68 |
"split_manifest": "splits/final_h100.json",
|
| 69 |
"split_seed": 142,
|
| 70 |
"temperature": 1.34592281013039,
|
| 71 |
+
"vocab_size": 94,
|
| 72 |
"weight_decay": 0.01,
|
| 73 |
"width": 64
|
| 74 |
}
|
cnn/hf_model.py
ADDED
|
@@ -0,0 +1,176 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Standalone Transformers classes exported with Chandassu model packages.
|
| 2 |
+
|
| 3 |
+
Copyright 2026 Pranav Surampudi. SPDX-License-Identifier: LicenseRef-Chandassu-Citation
|
| 4 |
+
This module intentionally depends only on PyTorch, Transformers and the standard library.
|
| 5 |
+
"""
|
| 6 |
+
|
| 7 |
+
import json
|
| 8 |
+
import shutil
|
| 9 |
+
import unicodedata
|
| 10 |
+
from pathlib import Path
|
| 11 |
+
|
| 12 |
+
import torch
|
| 13 |
+
from torch import nn
|
| 14 |
+
from transformers import PretrainedConfig, PreTrainedModel, PreTrainedTokenizer, T5Config, T5EncoderModel
|
| 15 |
+
from transformers.modeling_outputs import SequenceClassifierOutput
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
class ChandassuConfig(PretrainedConfig):
|
| 19 |
+
"""Keep the original fitting configuration and calibrated temperature."""
|
| 20 |
+
|
| 21 |
+
def __init__(self, labels=None, temperature=1.0, calibration_temperature=None, **kwargs):
|
| 22 |
+
labels = labels or ["ఉత్పలమాల", "చంపకమాల", "మత్తేభము", "శార్దూలం"]
|
| 23 |
+
kwargs.setdefault("id2label", dict(enumerate(labels)))
|
| 24 |
+
kwargs.setdefault("label2id", {label: i for i, label in enumerate(labels)})
|
| 25 |
+
super().__init__(**kwargs)
|
| 26 |
+
self.labels = labels
|
| 27 |
+
self.calibration_temperature = temperature if calibration_temperature is None else calibration_temperature
|
| 28 |
+
if len(labels) != 4 or not 0 < self.calibration_temperature < float("inf"):
|
| 29 |
+
raise ValueError("Require four labels and a finite positive temperature")
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
class ChandassuCNNConfig(ChandassuConfig):
|
| 33 |
+
model_type = "cnn"
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
class ChandassuByT5Config(ChandassuConfig):
|
| 37 |
+
model_type = "byt5"
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
class ChandassuTokenizer(PreTrainedTokenizer):
|
| 41 |
+
"""Exact training-time NFC, whitespace, character and UTF-8 byte encoding."""
|
| 42 |
+
|
| 43 |
+
vocab_files_names = {"vocabulary_file": "vocabulary.json"}
|
| 44 |
+
model_input_names = ["input_ids", "attention_mask"]
|
| 45 |
+
|
| 46 |
+
def __init__(self, vocabulary_file, **kwargs):
|
| 47 |
+
self.vocabulary_file = str(vocabulary_file)
|
| 48 |
+
saved = json.loads(Path(vocabulary_file).read_text())
|
| 49 |
+
self.kind = saved["kind"]
|
| 50 |
+
self.limit = saved["max_tokens"]
|
| 51 |
+
if self.kind == "character":
|
| 52 |
+
self.tokens = {"[PAD]": 0, "[UNK]": 1, **saved["tokens"]}
|
| 53 |
+
defaults = {"pad_token": "[PAD]", "unk_token": "[UNK]"}
|
| 54 |
+
elif self.kind == "utf8_bytes":
|
| 55 |
+
self.tokens = {"<pad>": 0, "</s>": 1, "<unk>": 2}
|
| 56 |
+
self.tokens.update({f"<byte:{i}>": i + 3 for i in range(256)})
|
| 57 |
+
defaults = {"pad_token": "<pad>", "eos_token": "</s>", "unk_token": "<unk>"}
|
| 58 |
+
else:
|
| 59 |
+
raise ValueError("Unsupported vocabulary kind")
|
| 60 |
+
self.reverse_tokens = {value: key for key, value in self.tokens.items()}
|
| 61 |
+
for key, value in defaults.items():
|
| 62 |
+
kwargs.setdefault(key, value)
|
| 63 |
+
kwargs.setdefault("model_max_length", self.limit)
|
| 64 |
+
kwargs.setdefault("padding_side", "right")
|
| 65 |
+
super().__init__(**kwargs)
|
| 66 |
+
|
| 67 |
+
@property
|
| 68 |
+
def vocab_size(self):
|
| 69 |
+
return len(self.tokens)
|
| 70 |
+
|
| 71 |
+
def get_vocab(self):
|
| 72 |
+
return dict(self.tokens, **self.added_tokens_encoder)
|
| 73 |
+
|
| 74 |
+
def tokenize(self, text, **kwargs):
|
| 75 |
+
# Override special-token splitting: literal text must have the same IDs as training.
|
| 76 |
+
text = " ".join(unicodedata.normalize("NFC", text).replace("\ufeff", "").split())
|
| 77 |
+
if self.kind == "character":
|
| 78 |
+
if not text or len(text) > self.limit:
|
| 79 |
+
raise ValueError(f"Line length outside 1..{self.limit}; no truncation")
|
| 80 |
+
return list(text)
|
| 81 |
+
encoded = text.encode("utf-8")
|
| 82 |
+
if len(encoded) + 1 > self.limit:
|
| 83 |
+
raise ValueError("Byte line exceeds capacity; no truncation")
|
| 84 |
+
return [f"<byte:{value}>" for value in encoded]
|
| 85 |
+
|
| 86 |
+
def _tokenize(self, text):
|
| 87 |
+
return self.tokenize(text)
|
| 88 |
+
|
| 89 |
+
def _convert_token_to_id(self, token):
|
| 90 |
+
return self.tokens.get(token, self.tokens[str(self.unk_token)])
|
| 91 |
+
|
| 92 |
+
def _convert_id_to_token(self, index):
|
| 93 |
+
return self.reverse_tokens.get(index, str(self.unk_token))
|
| 94 |
+
|
| 95 |
+
def convert_tokens_to_string(self, tokens):
|
| 96 |
+
if self.kind == "character":
|
| 97 |
+
return "".join(tokens)
|
| 98 |
+
return bytes(int(t[6:-1]) for t in tokens if t.startswith("<byte:")).decode("utf-8", errors="replace")
|
| 99 |
+
|
| 100 |
+
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
|
| 101 |
+
if token_ids_1 is not None:
|
| 102 |
+
raise ValueError("Encode poem lines separately; text pairs are unsupported")
|
| 103 |
+
return token_ids_0 + ([1] if self.kind == "utf8_bytes" else [])
|
| 104 |
+
|
| 105 |
+
def get_special_tokens_mask(self, token_ids_0, token_ids_1=None, already_has_special_tokens=False):
|
| 106 |
+
if already_has_special_tokens:
|
| 107 |
+
return super().get_special_tokens_mask(token_ids_0, token_ids_1, True)
|
| 108 |
+
return [0] * len(token_ids_0) + ([1] if self.kind == "utf8_bytes" else [])
|
| 109 |
+
|
| 110 |
+
def prepare_for_model(self, *args, **kwargs):
|
| 111 |
+
if kwargs.get("truncation") not in (None, False, "do_not_truncate"):
|
| 112 |
+
raise ValueError("Truncation is unsupported; supply a complete line within the input limit")
|
| 113 |
+
return super().prepare_for_model(*args, **kwargs)
|
| 114 |
+
|
| 115 |
+
def save_vocabulary(self, save_directory, filename_prefix=None):
|
| 116 |
+
name = (filename_prefix + "-" if filename_prefix else "") + "vocabulary.json"
|
| 117 |
+
destination = Path(save_directory) / name
|
| 118 |
+
if destination.resolve() != Path(self.vocabulary_file).resolve():
|
| 119 |
+
shutil.copyfile(self.vocabulary_file, destination)
|
| 120 |
+
return (str(destination),)
|
| 121 |
+
|
| 122 |
+
|
| 123 |
+
class ChandassuClassifier(PreTrainedModel):
|
| 124 |
+
"""Four raw line logits; use config.calibration_temperature for calibrated probabilities."""
|
| 125 |
+
|
| 126 |
+
config_class = ChandassuConfig
|
| 127 |
+
_tied_weights_keys = ["encoder.encoder.embed_tokens.weight"]
|
| 128 |
+
|
| 129 |
+
def __init__(self, config):
|
| 130 |
+
super().__init__(config)
|
| 131 |
+
self.dropout = nn.Dropout(config.dropout)
|
| 132 |
+
if config.model_type == "cnn":
|
| 133 |
+
self.embedding = nn.Embedding(config.vocab_size, config.width, padding_idx=0)
|
| 134 |
+
self.convolutions = nn.ModuleList(
|
| 135 |
+
[nn.Conv1d(config.width, config.width, k, padding=k // 2) for k in config.kernel_sizes]
|
| 136 |
+
)
|
| 137 |
+
self.classifier = nn.Linear(config.width * len(config.kernel_sizes), 4)
|
| 138 |
+
elif config.model_type == "byt5":
|
| 139 |
+
self.encoder = T5EncoderModel(T5Config.from_dict(config.encoder_config))
|
| 140 |
+
self.classifier = nn.Linear(self.encoder.config.d_model, 4)
|
| 141 |
+
else:
|
| 142 |
+
raise ValueError("Unsupported model family")
|
| 143 |
+
self.post_init()
|
| 144 |
+
|
| 145 |
+
def forward(self, input_ids, attention_mask=None, labels=None, return_dict=None, **kwargs):
|
| 146 |
+
valid = input_ids.ne(0)
|
| 147 |
+
if not valid.any(1).all():
|
| 148 |
+
raise ValueError("Empty line")
|
| 149 |
+
if attention_mask is not None and not torch.equal(attention_mask.bool(), valid):
|
| 150 |
+
raise ValueError("Attention mask must match non-padding token IDs")
|
| 151 |
+
if self.config.model_type == "cnn":
|
| 152 |
+
embedded = self.embedding(input_ids).masked_fill(~valid.unsqueeze(-1), 0.0)
|
| 153 |
+
features = self.dropout(embedded).transpose(1, 2)
|
| 154 |
+
pooled = torch.cat(
|
| 155 |
+
[
|
| 156 |
+
torch.relu(conv(features)).masked_fill(~valid.unsqueeze(1), float("-inf")).amax(2)
|
| 157 |
+
for conv in self.convolutions
|
| 158 |
+
],
|
| 159 |
+
dim=1,
|
| 160 |
+
)
|
| 161 |
+
else:
|
| 162 |
+
hidden = self.encoder(input_ids=input_ids, attention_mask=valid.long(), return_dict=True).last_hidden_state
|
| 163 |
+
pooled = (hidden * valid.unsqueeze(-1)).sum(1) / valid.sum(1, keepdim=True)
|
| 164 |
+
logits = self.classifier(self.dropout(pooled))
|
| 165 |
+
loss = nn.functional.cross_entropy(logits, labels) if labels is not None else None
|
| 166 |
+
if return_dict is False or (return_dict is None and not self.config.use_return_dict):
|
| 167 |
+
return (loss, logits) if loss is not None else (logits,)
|
| 168 |
+
return SequenceClassifierOutput(loss=loss, logits=logits)
|
| 169 |
+
|
| 170 |
+
|
| 171 |
+
class ChandassuCNNForSequenceClassification(ChandassuClassifier):
|
| 172 |
+
config_class = ChandassuCNNConfig
|
| 173 |
+
|
| 174 |
+
|
| 175 |
+
class ChandassuByT5ForSequenceClassification(ChandassuClassifier):
|
| 176 |
+
config_class = ChandassuByT5Config
|
cnn/manifest.json
CHANGED
|
@@ -1,8 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"files": {
|
| 3 |
-
"config.json": "
|
|
|
|
| 4 |
"metadata.json": "550c82d89c0cc8607c90f6b7ae5af99bd1ec62ab48754d84808c62258a42d731",
|
| 5 |
"model.safetensors": "6d8d642f8b83343e6e98c90365b1449acf0fcedf430f4b4e727a01979aa4e95e",
|
|
|
|
| 6 |
"vocabulary.json": "6d3991cf7463459f411f6e3bc03bc5f14b4274a712e6853d784c00835ce14cee"
|
| 7 |
},
|
| 8 |
"schema_version": 1
|
|
|
|
| 1 |
{
|
| 2 |
"files": {
|
| 3 |
+
"config.json": "fc5f10b725dfbb4e081f7789740361f14daa12eede4827cafff2517e442fc37a",
|
| 4 |
+
"hf_model.py": "d9b75c12812f843a8b4f95f275add3c946773f07a65c24d46be08f55edceb5e3",
|
| 5 |
"metadata.json": "550c82d89c0cc8607c90f6b7ae5af99bd1ec62ab48754d84808c62258a42d731",
|
| 6 |
"model.safetensors": "6d8d642f8b83343e6e98c90365b1449acf0fcedf430f4b4e727a01979aa4e95e",
|
| 7 |
+
"tokenizer_config.json": "3ee891d67d5c1c0b7c6eb08e537ab973c9dc77eed067ee64ea36c59ba7a1e91a",
|
| 8 |
"vocabulary.json": "6d3991cf7463459f411f6e3bc03bc5f14b4274a712e6853d784c00835ce14cee"
|
| 9 |
},
|
| 10 |
"schema_version": 1
|
cnn/tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_map": {
|
| 3 |
+
"AutoTokenizer": [
|
| 4 |
+
"hf_model.ChandassuTokenizer",
|
| 5 |
+
null
|
| 6 |
+
]
|
| 7 |
+
},
|
| 8 |
+
"model_max_length": 256,
|
| 9 |
+
"padding_side": "right",
|
| 10 |
+
"tokenizer_class": "ChandassuTokenizer"
|
| 11 |
+
}
|