Upload XLMRobertaForSequenceClassification
Browse files- config.json +23 -17
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,24 +1,30 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
-
"activation": "gelu",
|
| 4 |
"architectures": [
|
| 5 |
-
"
|
| 6 |
],
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
"
|
| 18 |
-
"
|
| 19 |
-
"
|
| 20 |
-
"
|
|
|
|
| 21 |
"torch_dtype": "float32",
|
| 22 |
"transformers_version": "4.48.3",
|
| 23 |
-
"
|
|
|
|
|
|
|
| 24 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "castorini/afriberta_base",
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 5 |
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_length": 512,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "xlm-roberta",
|
| 20 |
+
"num_attention_heads": 6,
|
| 21 |
+
"num_hidden_layers": 8,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 1,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
"torch_dtype": "float32",
|
| 26 |
"transformers_version": "4.48.3",
|
| 27 |
+
"type_vocab_size": 1,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 70006
|
| 30 |
}
|
model.safetensors
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 sha256:2c6722b8e56e956728008bd38d956f88ad20151c021e174bcd69cb65241ab1a9
|
| 3 |
+
size 445843464
|