Nishith Jain

KingNish

AI & ML interests

Trying to make AI fun and Easy for Non-Techy.

Articles

Organizations

KingNish's activity

replied to merve's post 2 days ago
view reply

how to access??
any Sample Space Please.

replied to their post 2 days ago
posted an update 4 days ago
view post
Post
2165
OpenGPT 4o NEW UPDATES:
1. Dedicated Image and Video Engine
2. Model Choices for Voice Chat
3. Better and Faster Voice Chat
4. Various Bug fixes

Test and give feedback of New features:
KingNish/OpenGPT-4o

Future Updates:
1. Web Search (Suggested by @GPT007 and @Saionton )
2. Live Chat with Voice Chat
3. Model Choices (Suggested by @NotAiLOL )
4. Multilingual Chats.

Suggest more features that should be added. 🤗
Thanks!
·
replied to their post 4 days ago
view reply

Start with Learning basic Python
Then Learn from Other spaces how they work.
Always stay Curious.

replied to their post 4 days ago
replied to their post 4 days ago
view reply

Garmi ka aanand le rhe, Pak me garmi kesi par rhi h

replied to their post 4 days ago
replied to their post 4 days ago
replied to their post 4 days ago
view reply

Amazing, Its Fast and provides various customizations.

replied to their post 4 days ago
replied to fdaudens's post 5 days ago
view reply

Amazing, It could even respond to the question posed in five different languages.

image.png

replied to their post 7 days ago
view reply

@Saionton Created new dedicated image generation module and 1st model there is DallE. its working super fine.
Thanks for suggestion.

replied to their post 7 days ago
replied to their post 7 days ago
view reply

Lots of restrictions by Microsoft.
But some people gonna remove restrictions 🤣.

posted an update 8 days ago
view post
Post
4461
Microsoft Just Launched 3 Powerful Models

1. Phi 3 Medium (4k and 128k): A 14b Instruct tuned models that outperformed big models like Command R+ (104b), GPT 3.5 Pro, Gemini Pro, and is highly competitive with top models such as Mixtral 8x22b, Llama3 70B, and GPT 4.
microsoft/Phi-3-medium-4k-instruct
DEMO: Walmart-the-bag/Phi-3-Medium

2. Phi 3 Mini Vision 128k: A 4.5 billion-parameter, instruction-tuned vision model that has outperformed models such as Llava3 and Claude 3, and is providing stiff competition to Gemini 1Pro Vision.
microsoft/Phi-3-vision-128k-instruct

3. Phi3 Small (8k and 128k): Better than Llama3 8b, Mixtral 8x7b and GPT 3.5 turbo.
microsoft/Phi-3-small-128k-instruct
·
replied to their post 8 days ago
view reply

Why not use bigger computer vision model?i think we already reached enough improvement in language models.we need to focus on text to image and image to text models

Because bigger model requires bigger spaces and also slow down output.

replied to their post 8 days ago
replied to hakunamatata1997's post 8 days ago
view reply

but what about updating them or making them private.

replied to their post 8 days ago
replied to ehristoforu's post 9 days ago
replied to their post 9 days ago
view reply

Currently, I use the Pollination API, which is weak in generating text in images.
But in next update, I'm definitely going to add another powerful image generator.

replied to their post 9 days ago
view reply

Well, its speed depends on how many people are using it simultaneously, but let's see if there is a method to increase its speed from my side.

posted an update 10 days ago
view post
Post
4883
Decoding GPT-4'o': Its Mechanisms and Creating Similar AI.

𝗥𝗲𝗮𝗱 𝗙𝘂𝗹𝗹 𝐀𝐫𝐭𝐢𝐜𝐥𝐞: https://huggingface.co/blog/KingNish/decoding-gpt-4o

𝐒𝐮𝐦𝐦𝐚𝐫𝐲 𝐨𝐟 𝐀𝐫𝐭𝐢𝐜𝐥𝐞- 📝
# 𝐌𝐞𝐜𝐡𝐚𝐧𝐢𝐜𝐬 𝐨𝐟 𝐆𝐏𝐓-𝟒’𝐨’: GPT-4’o’ operates through three main components 🛠️

𝟏. 𝐒𝐮𝐩𝐞𝐫𝐂𝐡𝐚𝐭: Integrates image generation, QnA (image, document and video) for diverse interactions.
𝟐. 𝐕𝐨𝐢𝐜𝐞 𝐂𝐡𝐚𝐭: Merges TTS and STT for real-time, human-like audio responses, focusing on human interaction.
𝟑. 𝐕𝐢𝐝𝐞𝐨 𝐂𝐡𝐚𝐭: Utilizes Zero Shot Image Classification to enhance user interaction with visual information.

# 𝐌𝐞𝐭𝐡𝐨𝐝𝐬 𝐭𝐨 𝐂𝐫𝐞𝐚𝐭𝐞 𝐒𝐢𝐦𝐢𝐥𝐚𝐫 𝐀𝐈 🧠

𝟏. 𝐌𝐮𝐥𝐭𝐢𝐌𝐨𝐝𝐚𝐥𝐢𝐟𝐢𝐜𝐚𝐭𝐢𝐨𝐧: Combines multiple models for a powerful, multifunctional AI.
𝟐. 𝐃𝐮𝐜𝐭 𝐓𝐚𝐩𝐞 𝐌𝐞𝐭𝐡𝐨𝐝: Uses different models or APIs for specific tasks without additional training.

The article provides an in-depth exploration of GPT-4’o’, its functionalities, and methods to create similar AI models. It emphasizes the model’s language support and its innovative approach to human-AI interaction. 💡🌐

(𝙉𝙊𝙏𝙀: 𝙎𝙪𝙢𝙢𝙖𝙧𝙮 𝙞𝙨 𝘼𝙄 𝙜𝙚𝙣𝙚𝙧𝙖𝙩𝙚𝙙) ✅
  • 2 replies
·
replied to their post 10 days ago
view reply

Resolved the issue in live chat; it's now functioning properly.

replied to their post 10 days ago
replied to prabhatkr's post 11 days ago
view reply

@awacke1 Sanskrit could potentially have billions of words because of its flexibility.
For instance, consider the word "water" in Sanskrit; it has three distinct words for each tense—past, present, and future. These then branch into eight 'vibhaktis' or cases, each with a specific use in conversation, resulting in 24 variations of just one word.
Additionally, there are 280 synonyms for "water," leading to approximately 6720 words for a single concept. (Source: https://qr.ae/psiHhb )
This immense flexibility allows for the creation of new words by adhering to certain rules.
These leads to creation of billions of words.
For instance, consider the various names of people around the world; each person's name can be expressed in 24 different ways, depending on the tense and context.
This leads to more than billions of words in sanskrit.
Hope you understands.

replied to their post 11 days ago
posted an update 11 days ago
view post
Post
3480
New Updates OpenGPT 4o
1. Live Chat (also known as video chat) (very powerful and fast, it can even identify famous places and persons)
2. Powerful Image Generation

Test and give feedback of New features:
KingNish/OpenGPT-4o

Future Updates
1. PDF Chat
2. Human like speech (Using Parler tts expresso)
3. Multilingual support for voice chat

Suggest more features that should be added. 🤗

Edit: Live Chat is now very powerful (than prev)
·
replied to their post 11 days ago
view reply

Super Chat Model - Idefics 2
Image Generation Model - Pollination Ai Api
Speech to Text - Nemo (API)
Voice Chat (Base Model) - Mixtral 8x7b (Inference API)
Text to Speech - Edge tts (API)
Live Chat (base model) - uform gen2 dpo

is it possible to make a blog on how did you make it ?

Okay, after the video chat is completed.

replied to mrfakename's post 12 days ago
replied to their post 13 days ago
view reply

This implies that OpenAI provides a less robust model to free subscribers, as it appears to have weaker reasoning and mathematical capabilities.

replied to their post 13 days ago
replied to their post 14 days ago
posted an update 14 days ago
view post
Post
2785
Something is wrong with GPT-4o

Today, I gained access to GPT-4o, so I thought to test it. However, I encountered several problems, such as When I requested image generation, it did not create any images but only provided links, which are also incorrect. 😥 [Image 1]

Subsequently, I considered that my prompt might be incorrect, I attempted once more with a prompt from OpenAI's examples, but it also did not work. 😥 [Image 2]

Then, I tested its logical reasoning skills, which it failed. I presented a question that an 8b model solved with ease, but GPT-4o could not. 😥 [Image 3]

I also attempted to generate an image from another image, but this too was unsuccessful. [image 4]

Nonetheless, it excels in tasks such as image classification and voice chat.

If you've experienced similar issues, please share them here.
·
replied to their post 14 days ago
replied to their post 15 days ago
replied to victor's post 15 days ago
replied to victor's post 15 days ago
posted an update 15 days ago
view post
Post
3648
Introducing OpenGPT-4o
KingNish/OpenGPT-4o

Features:
1️⃣ Inputs possible are Text ✏️, Text + Image 📝🖼️, Audio 🎧, WebCam📸
and outputs possible are Image 🖼️, Image + Text 🖼️📝, Text 📝, Audio 🎧
2️⃣ Flat 100% FREE 💸 and Super-fast ⚡.
3️⃣ Publicly Available before GPT 4o.

Future Features:
1️⃣ Chat with PDF (Both voice and text)
2️⃣ Video generation.
3️⃣ Sequential Image Generation.
4️⃣ Better UI and customization.

Note: It's not possible to reach level of complexity of GPT 4o because OpenAI has been developing GPT-4o from six months with a team of over 450+ experienced members, Whereas I am only One. Moreover, they haven't released it fully publicly, So, it remains a test model.
·
replied to singhsidhukuldeep's post 15 days ago
replied to singhsidhukuldeep's post 15 days ago
replied to mwz's post 16 days ago
view reply

[ { "from": "human", "value": "Welcome, to HF" }]

posted an update 17 days ago
view post
Post
1746
JARVIS has been updated to include voice input functionality, allowing for an interactive experience similar to that of Siri and Alexa.
Check it out: KingNish/JARVIS
replied to their post 18 days ago
replied to osanseviero's post 19 days ago
replied to their post 19 days ago
replied to their post 21 days ago
posted an update 21 days ago
replied to their post 28 days ago
view reply

Hope to see this on Assistant of the WEEK page.

posted an update 28 days ago
replied to their post 29 days ago
view reply

Super fast! this is awesome!!

Thanks❤

replied to sosoai's post 29 days ago
posted an update 29 days ago
view post
Post
2579
Introducing JARVIS Tony's voice assistant for You.

JARVIS responds to all your questions in audio format.
Must TRY -> KingNish/JARVIS

Jarvis is currently equipped to accept text input and provide audio output.
In the future, it may also support audio input.

DEMO Video:
·
replied to sosoai's post 29 days ago
replied to victor's post 30 days ago
replied to fdaudens's post about 1 month ago
replied to abhishek's post about 1 month ago
replied to fdaudens's post about 1 month ago
view reply

Love to see on Android 🥰😍
Best of Luck😊

replied to thomwolf's post about 1 month ago
view reply

Can you give more info about bot like his capabilities and also keep us updated on its future update.