Upload BlipForConditionalGeneration

README.md

@@ -12,8 +12,8 @@ model-index:
 - name: fabric_classifier
   results:
   - task:
-      name: Image Classification
       type: image-classification
+      name: Image Classification
     dataset:
       name: arrow
       type: arrow
@@ -21,9 +21,9 @@ model-index:
       split: train
       args: default
     metrics:
-    - name: Accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.5
+      name: Accuracy
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

config.json

@@ -1,49 +1,52 @@
 {
   "architectures": [
-    "ViTForImageClassification"
+    "BlipForConditionalGeneration"
   ],
-  "attention_probs_dropout_prob": 0.0,
   "dtype": "float32",
-  "encoder_stride": 16,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "Cotton",
-    "1": "Silk",
-    "2": "Wool",
-    "3": "Polyester",
-    "4": "Denim",
-    "5": "Velvet",
-    "6": "Chanderi Silk",
-    "7": "Acrylic",
-    "8": "Cotton Silk",
-    "9": "Linen"
-  },
-  "image_size": 224,
+  "image_text_hidden_size": 256,
+  "initializer_factor": 1.0,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "Acrylic": 7,
-    "Chanderi Silk": 6,
-    "Cotton": 0,
-    "Cotton Silk": 8,
-    "Denim": 4,
-    "Linen": 9,
-    "Polyester": 3,
-    "Silk": 1,
-    "Velvet": 5,
-    "Wool": 2
+  "label_smoothing": 0.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "blip",
+  "projection_dim": 512,
+  "text_config": {
+    "attention_probs_dropout_prob": 0.0,
+    "dtype": "float32",
+    "encoder_hidden_size": 768,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "label_smoothing": 0.0,
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "model_type": "blip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "projection_dim": 768,
+    "use_cache": true,
+    "vocab_size": 30524
   },
-  "layer_norm_eps": 1e-12,
-  "model_type": "vit",
-  "num_attention_heads": 12,
-  "num_channels": 3,
-  "num_hidden_layers": 12,
-  "patch_size": 16,
-  "pooler_act": "tanh",
-  "pooler_output_size": 768,
-  "problem_type": "single_label_classification",
-  "qkv_bias": true,
-  "transformers_version": "4.57.0"
+  "transformers_version": "4.57.0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu",
+    "hidden_size": 768,
+    "image_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-05,
+    "model_type": "blip_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 512
+  }
 }

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 30522,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.57.0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ccedadf31fe966c7da4bfafc90fcac24808aee4a81772fea67adbc1b1e3055
-size 343248584
+oid sha256:026963a8993b3ad94f559582db605a5fbc7a8f647ee113d9428ec4d85abe609c
+size 895947208