Upload model
Browse files- config.json +15 -12
- generation_config.json +1 -1
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -7,6 +7,7 @@
|
|
| 7 |
"activation_dropout": 0.0,
|
| 8 |
"activation_function": "gelu",
|
| 9 |
"add_cross_attention": true,
|
|
|
|
| 10 |
"architectures": null,
|
| 11 |
"attention_dropout": 0.0,
|
| 12 |
"bad_words_ids": null,
|
|
@@ -17,7 +18,7 @@
|
|
| 17 |
"cross_attention_hidden_size": null,
|
| 18 |
"d_model": 16,
|
| 19 |
"decoder_attention_heads": 2,
|
| 20 |
-
"decoder_ffn_dim":
|
| 21 |
"decoder_layerdrop": 0.0,
|
| 22 |
"decoder_layers": 1,
|
| 23 |
"decoder_start_token_id": null,
|
|
@@ -26,7 +27,7 @@
|
|
| 26 |
"dropout": 0.1,
|
| 27 |
"early_stopping": false,
|
| 28 |
"encoder_attention_heads": 2,
|
| 29 |
-
"encoder_ffn_dim":
|
| 30 |
"encoder_layerdrop": 0.0,
|
| 31 |
"encoder_layers": 1,
|
| 32 |
"encoder_no_repeat_ngram_size": 0,
|
|
@@ -67,7 +68,7 @@
|
|
| 67 |
"repetition_penalty": 1.0,
|
| 68 |
"return_dict": true,
|
| 69 |
"return_dict_in_generate": false,
|
| 70 |
-
"scale_embedding":
|
| 71 |
"sep_token_id": null,
|
| 72 |
"suppress_tokens": null,
|
| 73 |
"task_specific_params": null,
|
|
@@ -97,6 +98,8 @@
|
|
| 97 |
"cross_attention_hidden_size": null,
|
| 98 |
"decoder_start_token_id": null,
|
| 99 |
"depths": [
|
|
|
|
|
|
|
| 100 |
2
|
| 101 |
],
|
| 102 |
"diversity_penalty": 0.0,
|
|
@@ -112,15 +115,12 @@
|
|
| 112 |
"forced_eos_token_id": null,
|
| 113 |
"hidden_act": "gelu",
|
| 114 |
"hidden_dropout_prob": 0.0,
|
| 115 |
-
"hidden_size":
|
| 116 |
"id2label": {
|
| 117 |
"0": "LABEL_0",
|
| 118 |
"1": "LABEL_1"
|
| 119 |
},
|
| 120 |
-
"image_size":
|
| 121 |
-
2560,
|
| 122 |
-
1920
|
| 123 |
-
],
|
| 124 |
"initializer_range": 0.02,
|
| 125 |
"is_decoder": false,
|
| 126 |
"is_encoder_decoder": false,
|
|
@@ -139,15 +139,18 @@
|
|
| 139 |
"num_beams": 1,
|
| 140 |
"num_channels": 3,
|
| 141 |
"num_heads": [
|
| 142 |
-
1
|
|
|
|
|
|
|
| 143 |
],
|
| 144 |
-
"num_layers":
|
| 145 |
"num_return_sequences": 1,
|
| 146 |
"output_attentions": false,
|
| 147 |
"output_hidden_states": false,
|
| 148 |
"output_scores": false,
|
| 149 |
"pad_token_id": null,
|
| 150 |
"patch_size": 4,
|
|
|
|
| 151 |
"prefix": null,
|
| 152 |
"problem_type": null,
|
| 153 |
"pruned_heads": {},
|
|
@@ -171,11 +174,11 @@
|
|
| 171 |
"typical_p": 1.0,
|
| 172 |
"use_absolute_embeddings": false,
|
| 173 |
"use_bfloat16": false,
|
| 174 |
-
"window_size":
|
| 175 |
},
|
| 176 |
"is_encoder_decoder": true,
|
| 177 |
"model_type": "vision-encoder-decoder",
|
| 178 |
"tie_word_embeddings": false,
|
| 179 |
"torch_dtype": "float32",
|
| 180 |
-
"transformers_version": "4.
|
| 181 |
}
|
|
|
|
| 7 |
"activation_dropout": 0.0,
|
| 8 |
"activation_function": "gelu",
|
| 9 |
"add_cross_attention": true,
|
| 10 |
+
"add_final_layer_norm": true,
|
| 11 |
"architectures": null,
|
| 12 |
"attention_dropout": 0.0,
|
| 13 |
"bad_words_ids": null,
|
|
|
|
| 18 |
"cross_attention_hidden_size": null,
|
| 19 |
"d_model": 16,
|
| 20 |
"decoder_attention_heads": 2,
|
| 21 |
+
"decoder_ffn_dim": 64,
|
| 22 |
"decoder_layerdrop": 0.0,
|
| 23 |
"decoder_layers": 1,
|
| 24 |
"decoder_start_token_id": null,
|
|
|
|
| 27 |
"dropout": 0.1,
|
| 28 |
"early_stopping": false,
|
| 29 |
"encoder_attention_heads": 2,
|
| 30 |
+
"encoder_ffn_dim": 64,
|
| 31 |
"encoder_layerdrop": 0.0,
|
| 32 |
"encoder_layers": 1,
|
| 33 |
"encoder_no_repeat_ngram_size": 0,
|
|
|
|
| 68 |
"repetition_penalty": 1.0,
|
| 69 |
"return_dict": true,
|
| 70 |
"return_dict_in_generate": false,
|
| 71 |
+
"scale_embedding": true,
|
| 72 |
"sep_token_id": null,
|
| 73 |
"suppress_tokens": null,
|
| 74 |
"task_specific_params": null,
|
|
|
|
| 98 |
"cross_attention_hidden_size": null,
|
| 99 |
"decoder_start_token_id": null,
|
| 100 |
"depths": [
|
| 101 |
+
2,
|
| 102 |
+
4,
|
| 103 |
2
|
| 104 |
],
|
| 105 |
"diversity_penalty": 0.0,
|
|
|
|
| 115 |
"forced_eos_token_id": null,
|
| 116 |
"hidden_act": "gelu",
|
| 117 |
"hidden_dropout_prob": 0.0,
|
| 118 |
+
"hidden_size": 384,
|
| 119 |
"id2label": {
|
| 120 |
"0": "LABEL_0",
|
| 121 |
"1": "LABEL_1"
|
| 122 |
},
|
| 123 |
+
"image_size": 224,
|
|
|
|
|
|
|
|
|
|
| 124 |
"initializer_range": 0.02,
|
| 125 |
"is_decoder": false,
|
| 126 |
"is_encoder_decoder": false,
|
|
|
|
| 139 |
"num_beams": 1,
|
| 140 |
"num_channels": 3,
|
| 141 |
"num_heads": [
|
| 142 |
+
1,
|
| 143 |
+
2,
|
| 144 |
+
4
|
| 145 |
],
|
| 146 |
+
"num_layers": 3,
|
| 147 |
"num_return_sequences": 1,
|
| 148 |
"output_attentions": false,
|
| 149 |
"output_hidden_states": false,
|
| 150 |
"output_scores": false,
|
| 151 |
"pad_token_id": null,
|
| 152 |
"patch_size": 4,
|
| 153 |
+
"path_norm": true,
|
| 154 |
"prefix": null,
|
| 155 |
"problem_type": null,
|
| 156 |
"pruned_heads": {},
|
|
|
|
| 174 |
"typical_p": 1.0,
|
| 175 |
"use_absolute_embeddings": false,
|
| 176 |
"use_bfloat16": false,
|
| 177 |
+
"window_size": 10
|
| 178 |
},
|
| 179 |
"is_encoder_decoder": true,
|
| 180 |
"model_type": "vision-encoder-decoder",
|
| 181 |
"tie_word_embeddings": false,
|
| 182 |
"torch_dtype": "float32",
|
| 183 |
+
"transformers_version": "4.44.2"
|
| 184 |
}
|
generation_config.json
CHANGED
|
@@ -4,5 +4,5 @@
|
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"forced_eos_token_id": 2,
|
| 6 |
"pad_token_id": 1,
|
| 7 |
-
"transformers_version": "4.
|
| 8 |
}
|
|
|
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"forced_eos_token_id": 2,
|
| 6 |
"pad_token_id": 1,
|
| 7 |
+
"transformers_version": "4.44.2"
|
| 8 |
}
|
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:c706f1405873012f46817ff5fd32e98f4e4b621fe07ef379c7472b4717a809cd
|
| 3 |
+
size 28133944
|