import from https://huggingface.co/distilroberta-base
Browse files- README.md +11 -0
- config.json +21 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- tokenizer.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
datasets:
|
| 5 |
+
- openwebtext
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# DistilRoBERTa base model
|
| 9 |
+
|
| 10 |
+
Forked from https://huggingface.co/distilroberta-base
|
| 11 |
+
|
config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"eos_token_id": 2,
|
| 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-05,
|
| 14 |
+
"max_position_embeddings": 514,
|
| 15 |
+
"model_type": "roberta",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 6,
|
| 18 |
+
"pad_token_id": 1,
|
| 19 |
+
"type_vocab_size": 1,
|
| 20 |
+
"vocab_size": 50265
|
| 21 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec1ed6ff4c9753d2fc41ddf4a63cc099697b6cfc308f3df668659e8d16f84c57
|
| 3 |
+
size 331070498
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|