Commit
•
c039b1c
1
Parent(s):
6a810bf
valid best lost
Browse files- config.json +8 -10
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,11 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"_commit_hash": "
|
| 3 |
-
"_name_or_path": "
|
| 4 |
"architectures": [
|
| 5 |
"Pix2StructForConditionalGeneration"
|
| 6 |
],
|
| 7 |
-
"
|
| 8 |
-
"decoder_start_token_id": 50344,
|
| 9 |
"eos_token_id": 1,
|
| 10 |
"initializer_factor": 1.0,
|
| 11 |
"initializer_range": 0.02,
|
|
@@ -28,7 +27,7 @@
|
|
| 28 |
"dense_act_fn": "gelu_new",
|
| 29 |
"diversity_penalty": 0.0,
|
| 30 |
"do_sample": false,
|
| 31 |
-
"dropout_rate": 0.
|
| 32 |
"early_stopping": false,
|
| 33 |
"encoder_hidden_size": 768,
|
| 34 |
"encoder_no_repeat_ngram_size": 0,
|
|
@@ -44,7 +43,7 @@
|
|
| 44 |
},
|
| 45 |
"initializer_factor": 1.0,
|
| 46 |
"initializer_range": 0.02,
|
| 47 |
-
"is_decoder":
|
| 48 |
"is_encoder_decoder": false,
|
| 49 |
"label2id": {
|
| 50 |
"LABEL_0": 0,
|
|
@@ -90,7 +89,7 @@
|
|
| 90 |
"typical_p": 1.0,
|
| 91 |
"use_bfloat16": false,
|
| 92 |
"use_cache": false,
|
| 93 |
-
"vocab_size":
|
| 94 |
},
|
| 95 |
"tie_word_embeddings": false,
|
| 96 |
"torch_dtype": "float32",
|
|
@@ -99,7 +98,7 @@
|
|
| 99 |
"_name_or_path": "",
|
| 100 |
"add_cross_attention": false,
|
| 101 |
"architectures": null,
|
| 102 |
-
"attention_dropout": 0.
|
| 103 |
"bad_words_ids": null,
|
| 104 |
"begin_suppress_tokens": null,
|
| 105 |
"bos_token_id": null,
|
|
@@ -111,7 +110,7 @@
|
|
| 111 |
"dense_act_fn": "gelu_new",
|
| 112 |
"diversity_penalty": 0.0,
|
| 113 |
"do_sample": false,
|
| 114 |
-
"dropout_rate": 0.
|
| 115 |
"early_stopping": false,
|
| 116 |
"encoder_no_repeat_ngram_size": 0,
|
| 117 |
"eos_token_id": null,
|
|
@@ -119,7 +118,6 @@
|
|
| 119 |
"finetuning_task": null,
|
| 120 |
"forced_bos_token_id": null,
|
| 121 |
"forced_eos_token_id": null,
|
| 122 |
-
"hidden_dropout_prob": 0.2,
|
| 123 |
"hidden_size": 768,
|
| 124 |
"id2label": {
|
| 125 |
"0": "LABEL_0",
|
|
|
|
| 1 |
{
|
| 2 |
+
"_commit_hash": "b5e9052166f90aa6cd57e09002bad39a9a7b9914",
|
| 3 |
+
"_name_or_path": "google/matcha-base",
|
| 4 |
"architectures": [
|
| 5 |
"Pix2StructForConditionalGeneration"
|
| 6 |
],
|
| 7 |
+
"decoder_start_token_id": 0,
|
|
|
|
| 8 |
"eos_token_id": 1,
|
| 9 |
"initializer_factor": 1.0,
|
| 10 |
"initializer_range": 0.02,
|
|
|
|
| 27 |
"dense_act_fn": "gelu_new",
|
| 28 |
"diversity_penalty": 0.0,
|
| 29 |
"do_sample": false,
|
| 30 |
+
"dropout_rate": 0.1,
|
| 31 |
"early_stopping": false,
|
| 32 |
"encoder_hidden_size": 768,
|
| 33 |
"encoder_no_repeat_ngram_size": 0,
|
|
|
|
| 43 |
},
|
| 44 |
"initializer_factor": 1.0,
|
| 45 |
"initializer_range": 0.02,
|
| 46 |
+
"is_decoder": true,
|
| 47 |
"is_encoder_decoder": false,
|
| 48 |
"label2id": {
|
| 49 |
"LABEL_0": 0,
|
|
|
|
| 89 |
"typical_p": 1.0,
|
| 90 |
"use_bfloat16": false,
|
| 91 |
"use_cache": false,
|
| 92 |
+
"vocab_size": 50352
|
| 93 |
},
|
| 94 |
"tie_word_embeddings": false,
|
| 95 |
"torch_dtype": "float32",
|
|
|
|
| 98 |
"_name_or_path": "",
|
| 99 |
"add_cross_attention": false,
|
| 100 |
"architectures": null,
|
| 101 |
+
"attention_dropout": 0.0,
|
| 102 |
"bad_words_ids": null,
|
| 103 |
"begin_suppress_tokens": null,
|
| 104 |
"bos_token_id": null,
|
|
|
|
| 110 |
"dense_act_fn": "gelu_new",
|
| 111 |
"diversity_penalty": 0.0,
|
| 112 |
"do_sample": false,
|
| 113 |
+
"dropout_rate": 0.0,
|
| 114 |
"early_stopping": false,
|
| 115 |
"encoder_no_repeat_ngram_size": 0,
|
| 116 |
"eos_token_id": null,
|
|
|
|
| 118 |
"finetuning_task": null,
|
| 119 |
"forced_bos_token_id": null,
|
| 120 |
"forced_eos_token_id": null,
|
|
|
|
| 121 |
"hidden_size": 768,
|
| 122 |
"id2label": {
|
| 123 |
"0": "LABEL_0",
|
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 sha256:160a695779f92ee5319563df01a0a3bf71d63c55d415025ea62f37d9767fa7c3
|
| 3 |
+
size 1129905601
|