adding model files

README.md

@@ -1,3 +1,42 @@
 ---
+language: en
 license: mit
+tags:
+- vision
+- image-to-text
+- image-captioning
+- visual-question-answering
+pipeline_tag: image-to-text
 ---
+
+# BLIP-2, OPT-6.7b, fine-tuned on COCO
+
+This is a fp16 version of the BLIP-2 model, leveraging [OPT-6.7b](https://huggingface.co/facebook/opt-6.7b) (a large language model with 6.7 billion parameters).
+It was introduced in the paper [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://arxiv.org/abs/2301.12597) by Li et al. and first released in [this repository](https://github.com/salesforce/LAVIS/tree/main/projects/blip2).
+
+- Refer to the [original model card](https://huggingface.co/Salesforce/blip2-opt-6.7b-coco) for more details about the model description, intended uses, and limitations, as well as instructions for how to use the model on CPU and GPU in different precisions.
+
+
+## Model description
+
+BLIP-2 consists of 3 models: a CLIP-like image encoder, a Querying Transformer (Q-Former) and a large language model.
+
+The authors initialize the weights of the image encoder and large language model from pre-trained checkpoints and keep them frozen
+while training the Querying Transformer, which is a BERT-like Transformer encoder that maps a set of "query tokens" to query embeddings,
+which bridge the gap between the embedding space of the image encoder and the large language model.
+
+The goal for the model is simply to predict the next text token, giving the query embeddings and the previous text.
+
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/blip2_architecture.jpg"
+alt="drawing" width="600"/> 
+
+This allows the model to be used for tasks like:
+
+- image captioning
+- visual question answering (VQA)
+- chat-like conversations by feeding the image and the previous conversation as prompt to the model
+
+
+### How to use
+
+For code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/blip-2#transformers.Blip2ForConditionalGeneration.forward.example).

config.json

@@ -0,0 +1,255 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "Blip2ForConditionalGeneration"
+  ],
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "model_type": "blip-2",
+  "num_query_tokens": 32,
+  "qformer_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_frequency": 2,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_hidden_size": 1408,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "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_2_qformer",
+    "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,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "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": "4.29.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 30522
+  },
+  "text_config": {
+    "_name_or_path": "",
+    "_remove_final_layer_norm": false,
+    "activation_dropout": 0.0,
+    "activation_function": "relu",
+    "add_cross_attention": false,
+    "architectures": [
+      "OPTForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 2,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_layer_norm_before": true,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "enable_bias": true,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50118,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 16384,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 4096,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_elementwise_affine": true,
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 2048,
+    "min_length": 0,
+    "model_type": "opt",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 32,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 32,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": "</s>",
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "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": "float16",
+    "torchscript": false,
+    "transformers_version": "4.29.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50272,
+    "word_embed_proj_dim": 4096
+  },
+  "torch_dtype": "float16",
+  "transformers_version": null,
+  "use_decoder_only_language_model": true,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1408,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 364,
+    "initializer_factor": 1.0,
+    "initializer_range": 1e-10,
+    "intermediate_size": 6144,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "blip_2_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 39,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "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": "4.29.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "BlipImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "Blip2Processor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 364,
+    "width": 364
+  }
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ccc304a7d2b47e6904525a7d75e3e5248a68e3310f3f0d236a04c1ae5cc466b
+size 9969074883

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ae2521b9b89fe08e522c0ac99b0d7ca3c49ef15d106dc720af049a3d53d13c0
+size 5949854372

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "processor_class": "Blip2Processor",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}