Upload app.py, models and requirement file

app.py

@@ -0,0 +1,61 @@
+from transformers import Blip2ForConditionalGeneration
+from transformers import Blip2Processor
+from peft import PeftModel, PeftConfig
+import streamlit as st
+from PIL import Image
+import torch
+
+preprocess_ckp = "Salesforce/blip2-opt-2.7b" #Checkpoint path used for perprocess image
+base_model_ckp = "/model/blip2-opt-2.7b-fp16-sharded" #Base model checkpoint path
+peft_model_ckp = "/model/blip2_peft" #PEFT model checkpoint path
+        
+init_model_required = True
+processor = None
+model = None
+
+def init_model():
+
+    if init_model_required:
+
+        #Preprocess input 
+        processor = Blip2Processor.from_pretrained(preprocess_ckp)
+
+        #Model        
+        model = Blip2ForConditionalGeneration.from_pretrained(base_model_ckp, load_in_8bit = True, device_map = "auto")
+        model = PeftModel.from_pretrained(model, peft_model_ckp)
+
+        init_model_required = False
+
+    
+
+def main():
+
+    st.title("Fashion Image Caption using BLIP2")
+
+    init_model()
+
+    file_name = st.file_uploader("Upload image")
+
+    if file_name is not None:
+
+        image_col, caption_text = st.columns(2)
+
+        image_col.header("Image")
+        image = Image.open(file_name)
+        image_col.image(image, use_column_width = True)
+
+        #Preprocess the image
+        inputs = processor(images = image, return_tensors = "pt").to('cuda', torch.float16)
+        pixel_values = inputs.pixel_values
+
+        #Predict the caption for the imahe
+        generated_ids = model.generate(pixel_values = pixel_values, max_length = 25)
+        generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]  
+
+        #Output the predict text
+        caption_text.header("Generated Caption")
+        caption_text.text(generated_caption)
+
+
+if __name__ == "__main__":
+    main()

model/blip2-opt-2.7b-fp16-sharded/config.json

@@ -0,0 +1,256 @@
+{
+  "_commit_hash": "56e1fe81e7e7c346e95e196ace7b442b3f8ff483",
+  "_name_or_path": "Salesforce/blip2-opt-2.7b",
+  "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": "4.28.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 30522
+  },
+  "text_config": {
+    "_name_or_path": "facebook/opt-2.7b",
+    "_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": 10240,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 2560,
+    "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": "4.28.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50272,
+    "word_embed_proj_dim": 2560
+  },
+  "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": 224,
+    "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": "4.28.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

model/blip2-opt-2.7b-fp16-sharded/gitattributes.txt

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

model/blip2-opt-2.7b-fp16-sharded/pytorch_model-00001-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca5d94b1b9b79c04040e7f559f9eafe87bbf8945d561a3137d77469dec462d01
+size 995214350

model/blip2-opt-2.7b-fp16-sharded/pytorch_model-00002-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:188085467c4048561813a1437066dac1d0275dfdb7e330715b1bf33e74b6ac94
+size 998967299

model/blip2-opt-2.7b-fp16-sharded/pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a3322729220657bdc4939a5a51ac075dc5a056cdc01b5cd0e5f80a94369d1d3
+size 984677387

model/blip2-opt-2.7b-fp16-sharded/pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a3853141772689f0acc1aa63c4179103af8dcdc3c495a148511b08e014ad5c8
+size 996601523

model/blip2-opt-2.7b-fp16-sharded/pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c93a6ad92db10aafac07cbde5be6a13a8ae673f932fd27400c1774ff82109d
+size 996597207

model/blip2-opt-2.7b-fp16-sharded/pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e3c47cf5253e70b8fd5711ad91c436a7ede67994d2c18629c5524d7907ed23
+size 996614793

model/blip2-opt-2.7b-fp16-sharded/pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f284b66c24d213e9ab693f407266e287b22fa7968499c9574d9a2b8563d46c8e
+size 996601651

model/blip2-opt-2.7b-fp16-sharded/pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5a88adee7133f403afe662af567a41d02a9f7a91df3d4cdb364292394e05831
+size 781914313

model/blip2_peft/README.md

@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+### Framework versions
+
+
+- PEFT 0.4.0.dev0

model/blip2_peft/adapter_config.json

@@ -0,0 +1,20 @@
+{
+  "base_model_name_or_path": "ybelkada/blip2-opt-2.7b-fp16-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": null
+}

model/blip2_peft/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f489a10474cd7779c5b59da42164677f54f0c6c44e7365a2690be4d1e9052e3
+size 21020237

requirements.txt

@@ -0,0 +1,2 @@
+transformers==4.30.2
+pytorch==2.0.0