Update config.json

config.json

@@ -1,155 +1,51 @@
-{
-  "_name_or_path": "AutoTrain",
+
   "architectures": [
-    "MT5ForConditionalGeneration"
+    "T5ForConditionalGeneration"
   ],
-  "d_ff": 2816,
+  "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 1024,
+  "d_model": 512,
   "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
-  "max_length": 256,
-  "model_type": "mt5",
-  "num_decoder_layers": 24,
-  "num_heads": 16,
-  "num_layers": 24,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_heads": 8,
+  "num_layers": 6,
   "output_past": true,
   "pad_token_id": 0,
-  "padding": "max_length",
-  "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
-  "tokenizer_class": "T5Tokenizer",
-  "torch_dtype": "float32",
-  "transformers_version": "4.25.1",
-  "use_cache": true,
-  "vocab_size": 250100
-}# coding=utf-8
-# Copyright 2020 Mesh TensorFlow authors, T5 Authors and HuggingFace Inc. team.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-""" PyTorch mT5 model. """
-
-from ...utils import logging
-from ..t5.modeling_t5 import T5EncoderModel, T5ForConditionalGeneration, T5Model
-from .configuration_mt5 import MT5Config
-
-
-logger = logging.get_logger(__name__)
-
-_CONFIG_FOR_DOC = "T5Config"
-_TOKENIZER_FOR_DOC = "T5Tokenizer"
-
-
-
-[DOCS]
-class MT5Model(T5Model):
-    r"""
-    This class overrides :class:`~transformers.T5Model`. Please check the superclass for the appropriate documentation
-    alongside usage examples.
-
-    Examples::
-
-        >>> from transformers import MT5Model, T5Tokenizer
-        >>> model = MT5Model.from_pretrained("google/mt5-small")
-        >>> tokenizer = T5Tokenizer.from_pretrained("google/mt5-small")
-        >>> article = "UN Offizier sagt, dass weiter verhandelt werden muss in Syrien."
-        >>> summary = "Weiter Verhandlung in Syrien."
-        >>> inputs = tokenizer(article, return_tensors="pt")
-        >>> with tokenizer.as_target_tokenizer():
-        ...     labels = tokenizer(summary, return_tensors="pt")
-
-        >>> outputs = model(input_ids=inputs["input_ids"], decoder_input_ids=labels["input_ids"])
-        >>> hidden_states = outputs.last_hidden_state
-    """
-    model_type = "mt5"
-    config_class = MT5Config
-    _keys_to_ignore_on_load_missing = [
-        r"encoder\.embed_tokens\.weight",
-        r"decoder\.embed_tokens\.weight",
-        r"decoder\.block\.0\.layer\.1\.EncDecAttention\.relative_attention_bias\.weight",
-    ]
-    _keys_to_ignore_on_save = [
-        r"encoder\.embed_tokens\.weight",
-        r"decoder\.embed_tokens\.weight",
-    ]
-
-
-
-
-[DOCS]
-class MT5ForConditionalGeneration(T5ForConditionalGeneration):
-    r"""
-    This class overrides :class:`~transformers.T5ForConditionalGeneration`. Please check the superclass for the
-    appropriate documentation alongside usage examples.
-
-    Examples::
-
-        >>> from transformers import MT5ForConditionalGeneration, T5Tokenizer
-        >>> model = MT5ForConditionalGeneration.from_pretrained("google/mt5-small")
-        >>> tokenizer = T5Tokenizer.from_pretrained("google/mt5-small")
-        >>> article = "UN Offizier sagt, dass weiter verhandelt werden muss in Syrien."
-        >>> summary = "Weiter Verhandlung in Syrien."
-        >>> inputs = tokenizer(article, return_tensors="pt")
-        >>> with tokenizer.as_target_tokenizer():
-        ...     labels = tokenizer(summary, return_tensors="pt")
-
-        >>> outputs = model(**inputs,labels=labels["input_ids"])
-        >>> loss = outputs.loss
-    """
-
-    model_type = "mt5"
-    config_class = MT5Config
-    _keys_to_ignore_on_load_missing = [
-        r"encoder\.embed_tokens\.weight",
-    ]
-    _keys_to_ignore_on_save = [
-        r"encoder\.embed_tokens\.weight",
-    ]
-
-
-
-
-[DOCS]
-class MT5EncoderModel(T5EncoderModel):
-    r"""
-    This class overrides :class:`~transformers.T5EncoderModel`. Please check the superclass for the appropriate
-    documentation alongside usage examples.
-
-    Examples::
-
-        >>> from transformers import MT5EncoderModel, T5Tokenizer
-        >>> model = MT5EncoderModel.from_pretrained("google/mt5-small")
-        >>> tokenizer = T5Tokenizer.from_pretrained("google/mt5-small")
-        >>> article = "UN Offizier sagt, dass weiter verhandelt werden muss in Syrien."
-        >>> input_ids = tokenizer(article, return_tensors="pt").input_ids
-        >>> outputs = model(input_ids)
-        >>> hidden_state = outputs.last_hidden_state
-    """
-
-    model_type = "mt5"
-    config_class = MT5Config
-    _keys_to_ignore_on_load_missing = [
-        r"encoder\.embed_tokens\.weight",
-    ]
-    _keys_to_ignore_on_save = [
-        r"encoder\.embed_tokens\.weight",
-    ]
-
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_ru_to_ab": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate Russian to Abkhaz: "
+    },
+    "translation_ru_to_ab": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate Russian to Abkhaz: "
+    },
+    "translation_ru_to_ab": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate Russian to Abkhaz: "
+    }
+  },
+  "vocab_size": 32128
+}