Upload BlipForQuestionAnswering

config.json

@@ -1,30 +1,96 @@
 {
-  "_commit_hash": "9d4c0a5e156bd7f37ff9090bf3ee3eb947d6d181",
-  "_name_or_path": "microsoft/git-base-textvqa",
+  "_commit_hash": "99909119248dc49e49cd698ad685b3b646595a38",
+  "_name_or_path": "Salesforce/blip-vqa-base",
   "architectures": [
-    "GitForCausalLM"
+    "BlipForQuestionAnswering"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 101,
-  "classifier_dropout": null,
-  "eos_token_id": 102,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "image_text_hidden_size": 256,
+  "initializer_factor": 1.0,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 1024,
-  "model_type": "git",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 6,
-  "num_image_with_embedding": null,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "tie_word_embeddings": false,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "blip",
+  "projection_dim": 512,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 30522,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_hidden_size": 768,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "blip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 768,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": 102,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.31.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30524
+  },
   "torch_dtype": "float32",
   "transformers_version": null,
-  "use_cache": true,
   "vision_config": {
     "_name_or_path": "",
     "add_cross_attention": false,
@@ -46,13 +112,13 @@
     "finetuning_task": null,
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
-    "hidden_act": "quick_gelu",
+    "hidden_act": "gelu",
     "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
-    "image_size": 480,
+    "image_size": 384,
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
     "intermediate_size": 3072,
@@ -66,7 +132,7 @@
     "length_penalty": 1.0,
     "max_length": 20,
     "min_length": 0,
-    "model_type": "git_vision_model",
+    "model_type": "blip_vision_model",
     "no_repeat_ngram_size": 0,
     "num_attention_heads": 12,
     "num_beam_groups": 1,
@@ -102,6 +168,5 @@
     "transformers_version": "4.31.0",
     "typical_p": 1.0,
     "use_bfloat16": false
-  },
-  "vocab_size": 30522
+  }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f1a16651c21c8152260ff7d608d6bb5f000f19d047d654216437ad7f609bf48
-size 708744543
+oid sha256:ee21eba38a5fe5a707d537ac6327523f458285ac538210c0e15dc735c0546642
+size 1538963481