Update GUS-Net GPT-2 Medium (paper-clean, checkpoint-2788)
Browse files- config.json +17 -18
- pytorch_model.bin +1 -1
- tokenizer.json +16 -2
config.json
CHANGED
|
@@ -4,29 +4,28 @@
|
|
| 4 |
"architectures": [
|
| 5 |
"GPT2ForTokenClassification"
|
| 6 |
],
|
| 7 |
-
"attn_pdrop": 0.
|
| 8 |
"bos_token_id": 50256,
|
| 9 |
-
"
|
| 10 |
-
"embd_pdrop": 0.15,
|
| 11 |
"eos_token_id": 50256,
|
| 12 |
"id2label": {
|
| 13 |
-
"0": "
|
| 14 |
-
"1": "
|
| 15 |
-
"2": "
|
| 16 |
-
"3": "
|
| 17 |
-
"4": "
|
| 18 |
-
"5": "
|
| 19 |
-
"6": "
|
| 20 |
},
|
| 21 |
"initializer_range": 0.02,
|
| 22 |
"label2id": {
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
-
"
|
| 26 |
-
"
|
| 27 |
-
"
|
| 28 |
-
"
|
| 29 |
-
"
|
| 30 |
},
|
| 31 |
"layer_norm_epsilon": 1e-05,
|
| 32 |
"model_type": "gpt2",
|
|
@@ -41,7 +40,7 @@
|
|
| 41 |
"predict_special_tokens": true,
|
| 42 |
"problem_type": "multi_label_classification",
|
| 43 |
"reorder_and_upcast_attn": false,
|
| 44 |
-
"resid_pdrop": 0.
|
| 45 |
"scale_attn_by_inverse_layer_idx": false,
|
| 46 |
"scale_attn_weights": true,
|
| 47 |
"summary_activation": null,
|
|
|
|
| 4 |
"architectures": [
|
| 5 |
"GPT2ForTokenClassification"
|
| 6 |
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
|
|
|
| 10 |
"eos_token_id": 50256,
|
| 11 |
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6"
|
| 19 |
},
|
| 20 |
"initializer_range": 0.02,
|
| 21 |
"label2id": {
|
| 22 |
+
"LABEL_0": 0,
|
| 23 |
+
"LABEL_1": 1,
|
| 24 |
+
"LABEL_2": 2,
|
| 25 |
+
"LABEL_3": 3,
|
| 26 |
+
"LABEL_4": 4,
|
| 27 |
+
"LABEL_5": 5,
|
| 28 |
+
"LABEL_6": 6
|
| 29 |
},
|
| 30 |
"layer_norm_epsilon": 1e-05,
|
| 31 |
"model_type": "gpt2",
|
|
|
|
| 40 |
"predict_special_tokens": true,
|
| 41 |
"problem_type": "multi_label_classification",
|
| 42 |
"reorder_and_upcast_attn": false,
|
| 43 |
+
"resid_pdrop": 0.1,
|
| 44 |
"scale_attn_by_inverse_layer_idx": false,
|
| 45 |
"scale_attn_weights": true,
|
| 46 |
"summary_activation": null,
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1444599419
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6142802eb5b400eddaf019115e682b5b4a80b4f3a244c20519c7753b0cbcd291
|
| 3 |
size 1444599419
|
tokenizer.json
CHANGED
|
@@ -1,7 +1,21 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 50256,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 128,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 128
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 50256,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "<|endoftext|>"
|
| 18 |
+
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 50256,
|