Commit
•
7e8b6c8
1
Parent(s):
ac47d9d
Upload RobertaForCausalLM
Browse files- config.json +19 -32
- generation_config.json +4 -3
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,39 +1,26 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "gpt2",
|
| 3 |
-
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
-
"
|
| 6 |
],
|
| 7 |
-
"
|
| 8 |
-
"bos_token_id":
|
| 9 |
-
"
|
| 10 |
-
"eos_token_id":
|
|
|
|
|
|
|
|
|
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
"
|
| 18 |
-
"
|
| 19 |
-
"
|
| 20 |
-
"reorder_and_upcast_attn": false,
|
| 21 |
-
"resid_pdrop": 0.1,
|
| 22 |
-
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
-
"scale_attn_weights": true,
|
| 24 |
-
"summary_activation": null,
|
| 25 |
-
"summary_first_dropout": 0.1,
|
| 26 |
-
"summary_proj_to_labels": true,
|
| 27 |
-
"summary_type": "cls_index",
|
| 28 |
-
"summary_use_proj": true,
|
| 29 |
-
"task_specific_params": {
|
| 30 |
-
"text-generation": {
|
| 31 |
-
"do_sample": true,
|
| 32 |
-
"max_length": 50
|
| 33 |
-
}
|
| 34 |
-
},
|
| 35 |
"torch_dtype": "float32",
|
| 36 |
-
"transformers_version": "4.
|
|
|
|
| 37 |
"use_cache": true,
|
| 38 |
-
"vocab_size":
|
| 39 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
+
"RobertaForCausalLM"
|
| 4 |
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 514,
|
| 16 |
+
"model_type": "roberta",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 6,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"position_embedding_type": "absolute",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.30.2",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
"use_cache": true,
|
| 25 |
+
"vocab_size": 64001
|
| 26 |
}
|
generation_config.json
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
-
"bos_token_id":
|
| 4 |
-
"eos_token_id":
|
| 5 |
-
"
|
|
|
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 1,
|
| 6 |
+
"transformers_version": "4.30.2"
|
| 7 |
}
|
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 sha256:3a3e7f41b1e081215737f3cc35688340d1d1eac9273e2aa500c5ac41a8a2f2da
|
| 3 |
+
size 370973241
|