Training in progress, step 3
Browse files- config.json +58 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MiniLLaDA"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "configuration_mini_llada.MiniLLaDAConfig",
|
| 8 |
+
"AutoModel": "modeling_mini_llada.MiniLLaDA"
|
| 9 |
+
},
|
| 10 |
+
"backbone_config": {
|
| 11 |
+
"_name_or_path": "klue/roberta-large",
|
| 12 |
+
"architectures": [
|
| 13 |
+
"RobertaForMaskedLM"
|
| 14 |
+
],
|
| 15 |
+
"attention_probs_dropout_prob": 0.1,
|
| 16 |
+
"classifier_dropout": null,
|
| 17 |
+
"gradient_checkpointing": false,
|
| 18 |
+
"hidden_act": "gelu",
|
| 19 |
+
"hidden_dropout_prob": 0.1,
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 4096,
|
| 23 |
+
"layer_norm_eps": 1e-05,
|
| 24 |
+
"max_position_embeddings": 514,
|
| 25 |
+
"model_type": "roberta",
|
| 26 |
+
"num_attention_heads": 16,
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
+
"position_embedding_type": "absolute",
|
| 29 |
+
"tokenizer_class": "BertTokenizer",
|
| 30 |
+
"type_vocab_size": 1,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32000
|
| 33 |
+
},
|
| 34 |
+
"backbone_model_name": "klue/roberta-large",
|
| 35 |
+
"bos_token_id": 0,
|
| 36 |
+
"classifier_dropout": null,
|
| 37 |
+
"dtype": "float32",
|
| 38 |
+
"eos_token_id": 2,
|
| 39 |
+
"gradient_checkpointing": false,
|
| 40 |
+
"hidden_act": "gelu",
|
| 41 |
+
"hidden_dropout_prob": 0.1,
|
| 42 |
+
"hidden_size": 1024,
|
| 43 |
+
"initializer_range": 0.02,
|
| 44 |
+
"intermediate_size": 4096,
|
| 45 |
+
"layer_norm_eps": 1e-05,
|
| 46 |
+
"mask_token_id": 4,
|
| 47 |
+
"max_position_embeddings": 514,
|
| 48 |
+
"model_type": "mini-llada",
|
| 49 |
+
"num_attention_heads": 16,
|
| 50 |
+
"num_hidden_layers": 24,
|
| 51 |
+
"pad_token_id": 1,
|
| 52 |
+
"position_embedding_type": "absolute",
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"transformers_version": "4.57.3",
|
| 55 |
+
"type_vocab_size": 1,
|
| 56 |
+
"use_cache": true,
|
| 57 |
+
"vocab_size": 32000
|
| 58 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c567fc208b02e0dad57794d83a5b8eed8ac5a65778736de4aa45125c55c9390b
|
| 3 |
+
size 1346813136
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:972bcc8c4c27622b5142a675dc52fe8df6194e9ead424d64814dec9e580f0d7d
|
| 3 |
+
size 5969
|