Nishith Jain
AI & ML interests
Articles
Organizations
KingNish's activity
It transcribes audio in about 0.3 seconds.
KingNish/Realtime-whisper-large-v3-turbo
DEMO LINK:
KingNish/Live-Video-Chat
Its' super cool and realistic.
Demo by @OzzyGT (Must try):
OzzyGT/diffusers-fast-inpaint
I found some flaws in the pipelines, which I resolved, and now I am able to generate an approx similar quality image as Flux Schnell 4 steps in just 1 step.
Demo Link:
KingNish/Realtime-FLUX
It has now achieved latency <250 ms.
While its average latency is about 500ms.
KingNish/Voicee
This become Possible due to newly launched @sambanovasystems cloud.
You can also use your own API Key to get fastest speed.
You can get on from here: https://cloud.sambanova.ai/apis
For optimal performance use Google Chrome.
Please try Voicee and share your valuable feedback to help me further improve its performance and usability.
Thank you!
Thank you for reporting. Now, its working fine.
KingNish/Voicee
It achieved latency <500 ms.
While its average latency is 700ms.
It works best in Google Chrome.
Please try and give your feedbacks.
Thank you. ๐ค
- More Ways to Interact with other peoples.
- Suggest/Recommends of Models/Datasets/Spaces. (Just like Suggested for you posts )
https://huggingface.co/spaces/KingNish/OpenCHAT-mini/tree/main
Here is the link to the source code of that space.
Models: Use
Mistral 7b v0.3: Function Calling,
Llama 3 8b: General Chat,
Nous Hermes 2 Mixtral 8x7b DPO: Web Search Chat,
llava interleave qwen 0.5b: Visual Question Answering
KingNish/OpenCHAT-mini2
It has unlimited web search, vision and image generation.
Please take a look and share your review. Thank you! ๐ค
Smaller LLMs are better at generating diverse and unique responses due to their more focused training data and architecture. They can also adapt quickly to new information and generate responses based on specific context, which leads to more creative and interesting answers. On the other hand, large LLMs have broader knowledge but may not be as adept at generating highly original or creative responses.
The issue has been resolved now; thank you for reporting.
yes, I am using Mistral inference client for generating the output.
I used Mistral 7b v0.3 Instruct, but you can use any text-generation model.
The complete code is available here: https://github.com/KingNishHF/OpenGPT-4o/blob/main/chatbot.py
The extracted information is sent to a language model which distill this information into a concise format, ensuring that the summary is accurate and aligns with the question posed by the user.
what's your username
yes
Yes, of course.
I am utilizing two libraries:
- googlesearch to obtain the URLs of sites from which to extract data.
- BeautifulSoup4 to extract information from webpages.
Duplicate this space - https://huggingface.co/spaces/KingNish/OpenGPT-4o?duplicate=true
then you can configure this.
what happens?? is web search not good
ohh, its not working. thank for reporting issue. Gonna solve in some time.
This feature enhances the capabilities of OpenGPT 4o, allowing it to fetch and integrate the latest information from the web directly into its responses.
Try Now: KingNish/OpenGPT-4o
With WEB SEARCH, OpenGPT 4o becomes an even more versatile and dynamic AI, ready to assist with up-to-date data retrieval and analysis.
import accelerate and only use safetensors model.
1. Chat with Google Agent - This includes three AI models that allow you to converse with an AI, which provides answers by searching Google.
Demo Link: poscye/google-go
2. HelpingAI 9B - A model that surpassed all top AIs with the highest EQ benchmark score of 89.23. It specializes in understanding human emotions and responding in human style.
Demo Link: https://huggingface.co/spaces/Abhaykoul/HelpingAI-9B
Model Link: OEvortex/HelpingAI-9B
Blog Link: https://huggingface.co/blog/KingNish/helpingai-9b
My partner has dealt with the licenses. Actually, I'm not sure what he intends to do next, but for now, it is an open-source project.
Don't act like kid, First decide with your partner that project is opensource for lifetime or not.
This is a opensource project
Then why you confusing peoples with custom license. Choose any better license. like Apache 2.0 or any poplar.
@alan45x try helping AI from here https://huggingface.co/spaces/Abhaykoul/HelpingAI-9B
Yes, you can use them but...
with limitations like
You can't use DallE ๐ฅ,
You can't make Custom GPTs
And chat limit also๐ฅ.
But...
We already have an open-source alternative like Hugging Chat, where you can create your custom assistant, generate, edit images, without any chat limit.
Try both of them from here:
https://chatgpt.com/gpts
https://huggingface.co/chat
and don't forget to Give your review here ๐:
Thanks for reporting the issue.
You encountered the issue because you entered text before image.
But I solved the issue by adding dropdown menu to select task.
Well, AI automatically determines the task you want but if it hallucinates just select correct task type.
I wasn't aware of it before. I've tried it now, and it's better than the standard pix2pix; the outputs are even more realistic.
Thank you for the suggestion.๐ค
KingNish/Image-Gen-Pro
It is Expert in Text to Image generation, Sequential Image generation or Image Editing.
Examples:
how to access??
any Sample Space Please.
Thanks! ๐ค
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. ๐ค
Thanks!
Start with Learning basic Python
Then Learn from Other spaces how they work.
Always stay Curious.
46C h yha Indore me.
Garmi ka aanand le rhe, Pak me garmi kesi par rhi h
Me from Pakistan
Hello, Neighbour
you are from Germany
No, India
Amazing, Its Fast and provides various customizations.
@Niansuh
I am not able to check this.
@Saionton
Created new dedicated image generation module and 1st model there is DallE. its working super fine.
Thanks for suggestion.
Currently not, in future may be.
Lots of restrictions by Microsoft.
But some people gonna remove restrictions ๐คฃ.
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
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.
Can you suggest some tools??
but what about updating them or making them private.
yes
Cool, fast, and with excellent image quality.
Demo Link: https://huggingface.co/spaces/KingNish/SDXL-Flash
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.
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.
๐ฅ๐ฒ๐ฎ๐ฑ ๐๐๐น๐น ๐๐ซ๐ญ๐ข๐๐ฅ๐: https://huggingface.co/blog/KingNish/decoding-gpt-4o
๐๐ฎ๐ฆ๐ฆ๐๐ซ๐ฒ ๐จ๐ ๐๐ซ๐ญ๐ข๐๐ฅ๐- ๐
# ๐๐๐๐ก๐๐ง๐ข๐๐ฌ ๐จ๐ ๐๐๐-๐โ๐จโ: GPT-4โoโ operates through three main components ๐ ๏ธ
๐. ๐๐ฎ๐ฉ๐๐ซ๐๐ก๐๐ญ: Integrates image generation, QnA (image, document and video) for diverse interactions.
๐. ๐๐จ๐ข๐๐ ๐๐ก๐๐ญ: Merges TTS and STT for real-time, human-like audio responses, focusing on human interaction.
๐. ๐๐ข๐๐๐จ ๐๐ก๐๐ญ: Utilizes Zero Shot Image Classification to enhance user interaction with visual information.
# ๐๐๐ญ๐ก๐จ๐๐ฌ ๐ญ๐จ ๐๐ซ๐๐๐ญ๐ ๐๐ข๐ฆ๐ข๐ฅ๐๐ซ ๐๐ ๐ง
๐. ๐๐ฎ๐ฅ๐ญ๐ข๐๐จ๐๐๐ฅ๐ข๐๐ข๐๐๐ญ๐ข๐จ๐ง: Combines multiple models for a powerful, multifunctional AI.
๐. ๐๐ฎ๐๐ญ ๐๐๐ฉ๐ ๐๐๐ญ๐ก๐จ๐: Uses different models or APIs for specific tasks without additional training.
The article provides an in-depth exploration of GPT-4โoโ, its functionalities, and methods to create similar AI models. It emphasizes the modelโs language support and its innovative approach to human-AI interaction. ๐ก๐
(๐๐๐๐: ๐๐ช๐ข๐ข๐๐ง๐ฎ ๐๐จ ๐ผ๐ ๐๐๐ฃ๐๐ง๐๐ฉ๐๐) โ
Resolved the issue in live chat; it's now functioning properly.