Upload MorphT5AutoForConditionalGeneration
Browse files- config.json +5 -10
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,13 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
-
"auto_map": {
|
| 7 |
-
"AutoConfig": "mrapacz/interlinear-en-philta-emb-auto-diacritics-bh--modeling_morph_t5_auto.MorphT5Config",
|
| 8 |
-
"AutoModelForSeq2SeqLM": "mrapacz/interlinear-en-philta-emb-auto-diacritics-bh--modeling_morph_t5_auto.MorphT5ForConditionalGeneration",
|
| 9 |
-
"AutoTokenizer": "mrapacz/interlinear-en-philta-emb-auto-diacritics-bh--modeling_morph_t5_auto.MorphologicallyAwareTokenizer"
|
| 10 |
-
},
|
| 11 |
"d_ff": 2048,
|
| 12 |
"d_kv": 64,
|
| 13 |
"d_model": 768,
|
|
@@ -21,9 +16,9 @@
|
|
| 21 |
"is_encoder_decoder": true,
|
| 22 |
"is_gated_act": true,
|
| 23 |
"layer_norm_epsilon": 1e-06,
|
| 24 |
-
"model_type": "morph-t5",
|
| 25 |
"morph_compressed_embedding_size": 64,
|
| 26 |
-
"morph_vocabulary_size":
|
| 27 |
"num_decoder_layers": 12,
|
| 28 |
"num_heads": 12,
|
| 29 |
"num_layers": 12,
|
|
@@ -32,7 +27,7 @@
|
|
| 32 |
"relative_attention_max_distance": 128,
|
| 33 |
"relative_attention_num_buckets": 32,
|
| 34 |
"tie_word_embeddings": false,
|
| 35 |
-
"tokenizer_class": "
|
| 36 |
"torch_dtype": "float32",
|
| 37 |
"transformers_version": "4.31.0",
|
| 38 |
"use_cache": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "../workspaces/exp512_3_INTMT-6543/best_model",
|
| 3 |
"architectures": [
|
| 4 |
+
"MorphT5AutoForConditionalGeneration"
|
| 5 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"d_ff": 2048,
|
| 7 |
"d_kv": 64,
|
| 8 |
"d_model": 768,
|
|
|
|
| 16 |
"is_encoder_decoder": true,
|
| 17 |
"is_gated_act": true,
|
| 18 |
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "morph-t5-auto",
|
| 20 |
"morph_compressed_embedding_size": 64,
|
| 21 |
+
"morph_vocabulary_size": 688,
|
| 22 |
"num_decoder_layers": 12,
|
| 23 |
"num_heads": 12,
|
| 24 |
"num_layers": 12,
|
|
|
|
| 27 |
"relative_attention_max_distance": 128,
|
| 28 |
"relative_attention_num_buckets": 32,
|
| 29 |
"tie_word_embeddings": false,
|
| 30 |
+
"tokenizer_class": "morpht5.tokenizer.morph_t5_tokenizer.MorphT5Tokenizer",
|
| 31 |
"torch_dtype": "float32",
|
| 32 |
"transformers_version": "4.31.0",
|
| 33 |
"use_cache": true,
|
pytorch_model.bin
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 sha256:6f882cfc07e46442819df3676afeed98f49fe5b633ac1986b8037e5e06b23610
|
| 3 |
+
size 1187236414
|