Push model using huggingface_hub.
Browse files- config.json +3 -68
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,69 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
"contrastive_hidden_size": 768,
|
| 6 |
-
"drop_rate": 0.1,
|
| 7 |
-
"head_hidden_scale": 2,
|
| 8 |
-
"hidden_act": "gelu",
|
| 9 |
-
"hidden_size": 768,
|
| 10 |
-
"init_layernorm_from_vision_encoder": false,
|
| 11 |
-
"initializer_factor": 1,
|
| 12 |
-
"input_image_embed_size": 768,
|
| 13 |
-
"input_text_embed_size": 768,
|
| 14 |
-
"layer_norm_eps": 1e-05,
|
| 15 |
-
"link_tower_type": "add",
|
| 16 |
-
"logit_scale_init_value": 1.0,
|
| 17 |
-
"max_text_len": 50,
|
| 18 |
-
"mlp_ratio": 4,
|
| 19 |
-
"model_type": "bridgetower",
|
| 20 |
-
"num_attention_heads": 12,
|
| 21 |
-
"num_hidden_layers": 6,
|
| 22 |
-
"share_cross_modal_transformer_layers": true,
|
| 23 |
-
"share_link_tower_layers": false,
|
| 24 |
-
"text_config": {
|
| 25 |
-
"architectures": [
|
| 26 |
-
"BridgeTowerTextModel"
|
| 27 |
-
],
|
| 28 |
-
"attention_probs_dropout_prob": 0.1,
|
| 29 |
-
"classifier_dropout": null,
|
| 30 |
-
"hidden_act": "gelu",
|
| 31 |
-
"hidden_dropout_prob": 0.1,
|
| 32 |
-
"hidden_size": 768,
|
| 33 |
-
"initializer_factor": 1,
|
| 34 |
-
"initializer_range": 0.02,
|
| 35 |
-
"intermediate_size": 3072,
|
| 36 |
-
"layer_norm_eps": 1e-05,
|
| 37 |
-
"max_position_embeddings": 514,
|
| 38 |
-
"model_type": "bridgetower_text_model",
|
| 39 |
-
"num_attention_heads": 12,
|
| 40 |
-
"num_hidden_layers": 12,
|
| 41 |
-
"position_embedding_type": "absolute",
|
| 42 |
-
"torch_dtype": "float32",
|
| 43 |
-
"type_vocab_size": 1,
|
| 44 |
-
"use_cache": true,
|
| 45 |
-
"vocab_size": 50265
|
| 46 |
-
},
|
| 47 |
-
"tie_word_embeddings": false,
|
| 48 |
-
"torch_dtype": "float32",
|
| 49 |
-
"transformers_version": "4.53.3",
|
| 50 |
-
"vision_config": {
|
| 51 |
-
"architectures": [
|
| 52 |
-
"BridgeTowerVisionModel"
|
| 53 |
-
],
|
| 54 |
-
"hidden_size": 768,
|
| 55 |
-
"image_size": 288,
|
| 56 |
-
"init_layernorm_from_vit": false,
|
| 57 |
-
"initializer_factor": 1,
|
| 58 |
-
"layer_norm_eps": 1e-05,
|
| 59 |
-
"model_type": "bridgetower_vision_model",
|
| 60 |
-
"num_channels": 3,
|
| 61 |
-
"num_hidden_layers": 12,
|
| 62 |
-
"patch_size": 16,
|
| 63 |
-
"remove_last_layer": false,
|
| 64 |
-
"share_layernorm": true,
|
| 65 |
-
"stop_gradient": false,
|
| 66 |
-
"torch_dtype": "float32",
|
| 67 |
-
"vit_remove_last": false
|
| 68 |
-
}
|
| 69 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"num_classes": 75,
|
| 3 |
+
"num_hidden_layers": 3
|
| 4 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 sha256:82c7d47dafe5e10d9247347e3932812144fcecb8b58592ad1de90701e183ce3d
|
| 3 |
+
size 1334299428
|