Upload model

config.json

@@ -9,8 +9,8 @@
   "logit_scale_init_value": 2.6592,
   "model_type": "groupvit",
   "output_segmentation": false,
-  "projection_dim": 16,
-  "projection_intermediate_dim": 16,
+  "projection_dim": 64,
+  "projection_intermediate_dim": 4096,
   "text_config": {
     "_name_or_path": "",
     "add_cross_attention": false,
@@ -32,14 +32,14 @@
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
     "hidden_act": "quick_gelu",
-    "hidden_size": 8,
+    "hidden_size": 32,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
-    "intermediate_size": 16,
+    "intermediate_size": 37,
     "is_decoder": false,
     "is_encoder_decoder": false,
     "label2id": {
@@ -49,11 +49,11 @@
     "layer_norm_eps": 1e-05,
     "length_penalty": 1.0,
     "max_length": 20,
-    "max_position_embeddings": 77,
+    "max_position_embeddings": 512,
     "min_length": 0,
     "model_type": "groupvit_text_model",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 2,
+    "num_attention_heads": 4,
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_hidden_layers": 5,
@@ -83,7 +83,7 @@
     "transformers_version": "4.22.0.dev0",
     "typical_p": 1.0,
     "use_bfloat16": false,
-    "vocab_size": 49408
+    "vocab_size": 99
   },
   "text_config_dict": null,
   "torch_dtype": "float32",
@@ -119,7 +119,7 @@
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
     "hidden_act": "gelu",
-    "hidden_size": 8,
+    "hidden_size": 32,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
@@ -127,7 +127,7 @@
     "image_size": 224,
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
-    "intermediate_size": 1536,
+    "intermediate_size": 37,
     "is_decoder": false,
     "is_encoder_decoder": false,
     "label2id": {
@@ -140,7 +140,7 @@
     "min_length": 0,
     "model_type": "groupvit_vision_model",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 2,
+    "num_attention_heads": 4,
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_channels": 3,
@@ -160,7 +160,7 @@
     "output_hidden_states": false,
     "output_scores": false,
     "pad_token_id": null,
-    "patch_size": 16,
+    "patch_size": 2,
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4dd422bd85ae1f96d5f8fad32ef13c453efc55b7c3a690c6ab14d1df82306c8
-size 3246131
+oid sha256:a25617c44bccd28450fc05e6cb26d64a22b0ca28fb71d454944be50916a87df5
+size 5770035