Update README.md

README.md

@@ -6,26 +6,26 @@ tags:
 - GGUF
 - Image-Text-to-Text
 ---
-# Omnivision
+# OmniVLM
 
 ## 🔥 Latest Update
-- [Nov 27, 2024] **Model Improvements:** OmniVision v3 model's **GGUF file has been updated** in this Hugging Face Repo! ✨
+- [Nov 27, 2024] **Model Improvements:** OmniVLM v3 model's **GGUF file has been updated** in this Hugging Face Repo! ✨
 👉 Test these exciting changes in our [Hugging Face Space](https://huggingface.co/spaces/NexaAIDev/omnivlm-dpo-demo)
 
 
-- [Nov 22, 2024] **Model Improvements:** OmniVision v2 model's **GGUF file has been updated** in this Hugging Face Repo! ✨ Key Improvements Include:
+- [Nov 22, 2024] **Model Improvements:** OmniVLM v2 model's **GGUF file has been updated** in this Hugging Face Repo! ✨ Key Improvements Include:
   - Enhanced Art Descriptions
   - Better Complex Image Understanding 
   - Improved Anime Recognition
   - More Accurate Color and Detail Detection
   - Expanded World Knowledge
 
-We are continuously improving Omnivision-968M based on your valuable feedback! **More exciting updates coming soon - Stay tuned!** ⭐
+We are continuously improving OmniVLM-968M based on your valuable feedback! **More exciting updates coming soon - Stay tuned!** ⭐
 
 
 ## Introduction
 
-Omnivision is a compact, sub-billion (968M) multimodal model for processing both visual and text inputs, optimized for edge devices. Improved on LLaVA's architecture, it features:
+OmniVLM is a compact, sub-billion (968M) multimodal model for processing both visual and text inputs, optimized for edge devices. Improved on LLaVA's architecture, it features:
 
 - **9x Token Reduction**: Reduces image tokens from **729** to **81**, cutting latency and computational cost aggressively. Note that the computation of vision encoder and the projection part keep the same, but the computation of language model backbone is reduced due to 9X shorter image token span.
 - **Trustworthy Result**: Reduces hallucinations using **DPO** training from trustworthy data.
@@ -38,7 +38,7 @@ Omnivision is a compact, sub-billion (968M) multimodal model for processing both
 **Feedback:** Send questions or comments about the model in our [Discord](https://discord.gg/nexa-ai)
 
 ## Intended Use Cases
-Omnivision is intended for **Visual Question Answering** (answering questions about images) and **Image Captioning** (describing scenes in photos), making it ideal for on-device applications.
+OmniVLM is intended for **Visual Question Answering** (answering questions about images) and **Image Captioning** (describing scenes in photos), making it ideal for on-device applications.
 
 **Example Demo:**
 Generating captions for a 1046×1568 image on M4 Pro Macbook takes **< 2s processing time** and requires only 988 MB RAM and 948 MB Storage.
@@ -49,13 +49,13 @@ Generating captions for a 1046×1568 image on M4 Pro Macbook takes **< 2s proces
 
 ## Benchmarks
 
-Below we demonstrate a figure to show how Omnivision performs against nanollava. In all the tasks, Omnivision outperforms the previous world's smallest vision-language model.
+Below we demonstrate a figure to show how OmniVLM performs against nanollava. In all the tasks, OmniVLM outperforms the previous world's smallest vision-language model.
 
 <img src="benchmark.png" alt="Benchmark Radar Chart" style="width:500px;"/>
 
-We have conducted a series of experiments on benchmark datasets, including MM-VET, ChartQA, MMMU, ScienceQA, POPE to evaluate the performance of Omnivision.
+We have conducted a series of experiments on benchmark datasets, including MM-VET, ChartQA, MMMU, ScienceQA, POPE to evaluate the performance of OmniVLM.
 
-| Benchmark         | Nexa AI Omnivision v2 | Nexa AI Omnivision v1 | nanoLLAVA |
+| Benchmark         | Nexa AI OmniVLM v2 | Nexa AI OmniVLM v1 | nanoLLAVA |
 |-------------------|------------------------|------------------------|-----------|
 | ScienceQA (Eval)  | 71.0                  | 62.2                  | 59.0      |
 | ScienceQA (Test)  | 71.0                  | 64.5                  | 59.0      |
@@ -67,7 +67,7 @@ We have conducted a series of experiments on benchmark datasets, including MM-VE
 
 
 ## How to Use On Device
-In the following, we demonstrate how to run Omnivision locally on your device.
+In the following, we demonstrate how to run OmniVLM locally on your device.
 
 **Step 1: Install Nexa-SDK (local on-device inference framework)**
 
@@ -78,11 +78,11 @@ In the following, we demonstrate how to run Omnivision locally on your device.
 **Step 2: Then run the following code in your terminal**
 
 ```bash
-nexa run omnivision 
+nexa run OmniVLM 
 ```
 
 ## Model Architecture ##
-Omnivision's architecture consists of three key components:
+OmniVLM's architecture consists of three key components:
 
 - Base Language Model: Qwen2.5-0.5B-Instruct functions as the base model to process text inputs
 - Vision Encoder: SigLIP-400M operates at 384 resolution with 14×14 patch size to generate image embeddings
@@ -92,7 +92,7 @@ The vision encoder first transforms input images into embeddings, which are then
 
 ## Training
 
-We developed Omnivision through a three-stage training pipeline:
+We developed OmniVLM through a three-stage training pipeline:
 
 **Pretraining:**
 The initial stage focuses on establishing basic visual-linguistic alignments using image-caption pairs, during which only the projection layer parameters are unfrozen to learn these fundamental relationships.
@@ -103,12 +103,12 @@ We enhance the model's contextual understanding using image-based question-answe
 **Direct Preference Optimization (DPO):**
 The final stage implements DPO by first generating responses to images using the base model. A teacher model then produces minimally edited corrections while maintaining high semantic similarity with the original responses, focusing specifically on accuracy-critical elements. These original and corrected outputs form chosen-rejected pairs. The fine-tuning targeted at essential model output improvements without altering the model's core response characteristics
 
-## What's next for Omnivision?
-Omnivision is in early development and we are working to address current limitations:
+## What's next for OmniVLM?
+OmniVLM is in early development and we are working to address current limitations:
 - Expand DPO Training: Increase the scope of DPO (Direct Preference Optimization) training in an iterative process to continually improve model performance and response quality.
 - Improve document and text understanding
   
-In the long term, we aim to develop Omnivision as a fully optimized, production-ready solution for edge AI multimodal applications.
+In the long term, we aim to develop OmniVLM as a fully optimized, production-ready solution for edge AI multimodal applications.
 
 ### Follow us
-[Blogs](https://nexa.ai/blogs/omni-vision) | [Discord](https://discord.gg/nexa-ai) | [X(Twitter)](https://x.com/nexa_ai)
+[Blogs](https://nexa.ai/blogs/OmniVLM) | [Discord](https://discord.gg/nexa-ai) | [X(Twitter)](https://x.com/nexa_ai)