Update README.md

README.md

@@ -9,34 +9,32 @@ tags:
 pipeline_tag: image-to-text
 ---
 
-# BLIP-2, OPT-6.7b, fine-tuned on COCO
+# BLIP-2, OPT-6.7b, Fine-tuned on COCO - Unofficial FP16 Version
 
-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).
+This repository contains an unofficial version of the BLIP-2 model, leveraging [OPT-6.7b](https://huggingface.co/facebook/opt-6.7b), which has been fine-tuned on COCO and converted to FP16 for reduced model size and memory footprint.
 
-- 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.
+The original model, BLIP-2, 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).
 
+For a comprehensive understanding of the model, its description, intended uses, limitations, and instructions on usage with different hardware and precision settings, please refer to the [official model card](https://huggingface.co/Salesforce/blip2-opt-6.7b-coco).
 
-## Model description
+## Unofficial FP16 Version
 
-BLIP-2 consists of 3 models: a CLIP-like image encoder, a Querying Transformer (Q-Former) and a large language model.
+This version of the BLIP-2 model has been converted to use FP16 precision, which effectively reduces the model size and memory requirements. The conversion to FP16 can potentially accelerate the model's computation time on hardware with FP16 support, although it might slightly affect the model's performance due to reduced numerical precision.
 
-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.
+This unofficial FP16 version is ideal for situations where storage, memory, or computational resources are limited.
 
-The goal for the model is simply to predict the next text token, giving the query embeddings and the previous text.
+Please note, this is an **unofficial** repository and not maintained or endorsed by the original authors of the model. The FP16 conversion was conducted independently and any potential issues, limitations or discrepancies with the original model are not the responsibility of the original authors.
 
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/blip2_architecture.jpg"
-alt="drawing" width="600"/> 
+### How to use
 
-This allows the model to be used for tasks like:
+The usage of this FP16 version of the model is similar to the original model. For specific code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/blip-2#transformers.Blip2ForConditionalGeneration.forward.example).
 
-- image captioning
-- visual question answering (VQA)
-- chat-like conversations by feeding the image and the previous conversation as prompt to the model
+Please ensure to test the performance and accuracy of this FP16 model thoroughly in your specific use-case to confirm it meets your needs.
 
+This version can be used for tasks like:
 
-### How to use
+- image captioning
+- visual question answering (VQA)
+- chat-like conversations by feeding the image and the previous conversation as a prompt to the model
 
-For code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/blip-2#transformers.Blip2ForConditionalGeneration.forward.example).
+*Disclaimer: This is an unofficial version of the model and any potential issues or discrepancies from the official model are not the responsibility of the original authors.*