adding model files
Browse files- README.md +1 -1
- config.json +25 -0
- pytorch_model.bin +3 -0
- vocab.txt +0 -0
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
language: hy
|
| 3 |
tags:
|
| 4 |
-
-
|
| 5 |
- armenian
|
| 6 |
- mlm
|
| 7 |
- llm
|
|
|
|
| 1 |
---
|
| 2 |
language: hy
|
| 3 |
tags:
|
| 4 |
+
- exbert
|
| 5 |
- armenian
|
| 6 |
- mlm
|
| 7 |
- llm
|
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/dbfs/mnt/gumgum-research-sx/ak_scratch/hyebert/model_2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 514,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 6,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.21.2",
|
| 22 |
+
"type_vocab_size": 1,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 30000
|
| 25 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7813466c312b936ed599fa4ff9d6b2d8fccf34396255207afb0800d79b9c727d
|
| 3 |
+
size 266385003
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|