Trained with normal text replication
Browse files- config.json +101 -2
- pytorch_model.bin +1 -1
config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_commit_hash": null,
|
3 |
-
"_name_or_path": "
|
4 |
"architectures": [
|
5 |
"EncoderDecoderModel"
|
6 |
],
|
@@ -99,7 +99,106 @@
|
|
99 |
"vocab_size": 50265
|
100 |
},
|
101 |
"decoder_start_token_id": 0,
|
102 |
-
"encoder": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
103 |
"eos_token_id": 2,
|
104 |
"is_encoder_decoder": true,
|
105 |
"max_length": 1024,
|
|
|
1 |
{
|
2 |
"_commit_hash": null,
|
3 |
+
"_name_or_path": "calibrated-decoder",
|
4 |
"architectures": [
|
5 |
"EncoderDecoderModel"
|
6 |
],
|
|
|
99 |
"vocab_size": 50265
|
100 |
},
|
101 |
"decoder_start_token_id": 0,
|
102 |
+
"encoder": {
|
103 |
+
"_name_or_path": "facebook/mbart-large-cc25",
|
104 |
+
"_num_labels": 3,
|
105 |
+
"activation_dropout": 0.0,
|
106 |
+
"activation_function": "gelu",
|
107 |
+
"add_bias_logits": false,
|
108 |
+
"add_cross_attention": false,
|
109 |
+
"add_final_layer_norm": true,
|
110 |
+
"architectures": [
|
111 |
+
"MBartForConditionalGeneration"
|
112 |
+
],
|
113 |
+
"attention_dropout": 0.0,
|
114 |
+
"bad_words_ids": null,
|
115 |
+
"begin_suppress_tokens": null,
|
116 |
+
"bos_token_id": 0,
|
117 |
+
"chunk_size_feed_forward": 0,
|
118 |
+
"classif_dropout": 0.0,
|
119 |
+
"classifier_dropout": 0.0,
|
120 |
+
"cross_attention_hidden_size": null,
|
121 |
+
"d_model": 1024,
|
122 |
+
"decoder_attention_heads": 16,
|
123 |
+
"decoder_ffn_dim": 4096,
|
124 |
+
"decoder_layerdrop": 0.0,
|
125 |
+
"decoder_layers": 12,
|
126 |
+
"decoder_start_token_id": null,
|
127 |
+
"diversity_penalty": 0.0,
|
128 |
+
"do_sample": false,
|
129 |
+
"dropout": 0.1,
|
130 |
+
"early_stopping": false,
|
131 |
+
"encoder_attention_heads": 16,
|
132 |
+
"encoder_ffn_dim": 4096,
|
133 |
+
"encoder_layerdrop": 0.0,
|
134 |
+
"encoder_layers": 12,
|
135 |
+
"encoder_no_repeat_ngram_size": 0,
|
136 |
+
"eos_token_id": 2,
|
137 |
+
"exponential_decay_length_penalty": null,
|
138 |
+
"finetuning_task": null,
|
139 |
+
"forced_bos_token_id": null,
|
140 |
+
"forced_eos_token_id": 2,
|
141 |
+
"id2label": {
|
142 |
+
"0": "LABEL_0",
|
143 |
+
"1": "LABEL_1",
|
144 |
+
"2": "LABEL_2"
|
145 |
+
},
|
146 |
+
"init_std": 0.02,
|
147 |
+
"is_decoder": false,
|
148 |
+
"is_encoder_decoder": true,
|
149 |
+
"label2id": {
|
150 |
+
"LABEL_0": 0,
|
151 |
+
"LABEL_1": 1,
|
152 |
+
"LABEL_2": 2
|
153 |
+
},
|
154 |
+
"length_penalty": 1.0,
|
155 |
+
"max_length": 1024,
|
156 |
+
"max_position_embeddings": 1024,
|
157 |
+
"min_length": 0,
|
158 |
+
"model_type": "mbart",
|
159 |
+
"no_repeat_ngram_size": 0,
|
160 |
+
"normalize_before": true,
|
161 |
+
"normalize_embedding": true,
|
162 |
+
"num_beam_groups": 1,
|
163 |
+
"num_beams": 5,
|
164 |
+
"num_hidden_layers": 12,
|
165 |
+
"num_return_sequences": 1,
|
166 |
+
"output_attentions": false,
|
167 |
+
"output_hidden_states": false,
|
168 |
+
"output_past": true,
|
169 |
+
"output_scores": false,
|
170 |
+
"pad_token_id": 1,
|
171 |
+
"prefix": null,
|
172 |
+
"problem_type": null,
|
173 |
+
"pruned_heads": {},
|
174 |
+
"remove_invalid_values": false,
|
175 |
+
"repetition_penalty": 1.0,
|
176 |
+
"return_dict": true,
|
177 |
+
"return_dict_in_generate": false,
|
178 |
+
"scale_embedding": true,
|
179 |
+
"sep_token_id": null,
|
180 |
+
"static_position_embeddings": false,
|
181 |
+
"suppress_tokens": null,
|
182 |
+
"task_specific_params": {
|
183 |
+
"translation_en_to_ro": {
|
184 |
+
"decoder_start_token_id": 250020
|
185 |
+
}
|
186 |
+
},
|
187 |
+
"temperature": 1.0,
|
188 |
+
"tf_legacy_loss": false,
|
189 |
+
"tie_encoder_decoder": false,
|
190 |
+
"tie_word_embeddings": true,
|
191 |
+
"tokenizer_class": null,
|
192 |
+
"top_k": 50,
|
193 |
+
"top_p": 1.0,
|
194 |
+
"torch_dtype": null,
|
195 |
+
"torchscript": false,
|
196 |
+
"transformers_version": "4.25.1",
|
197 |
+
"typical_p": 1.0,
|
198 |
+
"use_bfloat16": false,
|
199 |
+
"use_cache": true,
|
200 |
+
"vocab_size": 250027
|
201 |
+
},
|
202 |
"eos_token_id": 2,
|
203 |
"is_encoder_decoder": true,
|
204 |
"max_length": 1024,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 639661093
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d90c8c589c8f5bd19d2a1af1c7373fdd8d4094e991dcd00f4970f1344ff04e4
|
3 |
size 639661093
|