the problem is the context check for the max seq length it have is smaller than the pdf so model forgets everything
Void
Parveshiiii
AI & ML interests
I love deep neural nets.
Recent Activity
published
a dataset
about 21 hours ago
Org-Exp/Audio
updated
a model
5 days ago
Org-Exp/M1-MathX
liked
a model
5 days ago
Org-Exp/M1-MathX
Organizations
replied to
their
post
6 days ago
replied to
their
post
6 days ago
im trying to teach my ai about topics, only ChatGpt can discuss properly...
i got may books pdf i tried uploading 1 by 1 to local model, but its not a fix, Ai go hallucinate
its new topic, new logic, ...
what is the context size of the model you are loading locally or what is the model you using
replied to
their
post
6 days ago
yup i can help you what's the problem
replied to
their
post
10 days ago
If you are beginner you should go for books for dl as there are no cources on internet those are actually useful as most of experts are earing more that what they would earn if they sell cources so I would suggest take any deep learning book and try to do practical learning. If you want video you can go for andrej karapathy yt playlist but it's not for beginner so read some books and research papers before watching ut
reacted to
their
post with 🔥
10 days ago
Post
3514
Hey everyone!
We’re excited to introduce our new Telegram group: https://t.me/XenArcAI
This space is built for **model builders, tech enthusiasts, and developers** who want to learn, share, and grow together. Whether you’re just starting out or already deep into AI/ML, you’ll find a supportive community ready to help with knowledge, ideas, and collaboration.
💡 Join us to:
- Connect with fellow developers and AI enthusiasts
- Share your projects, insights, and questions
- Learn from others and contribute to a growing knowledge base
👉 If you’re interested, hop in and be part of the conversation: https://t.me/XenArcAI
We’re excited to introduce our new Telegram group: https://t.me/XenArcAI
This space is built for **model builders, tech enthusiasts, and developers** who want to learn, share, and grow together. Whether you’re just starting out or already deep into AI/ML, you’ll find a supportive community ready to help with knowledge, ideas, and collaboration.
💡 Join us to:
- Connect with fellow developers and AI enthusiasts
- Share your projects, insights, and questions
- Learn from others and contribute to a growing knowledge base
👉 If you’re interested, hop in and be part of the conversation: https://t.me/XenArcAI
-
- 12 replies
posted
an
update
10 days ago
Post
3514
Hey everyone!
We’re excited to introduce our new Telegram group: https://t.me/XenArcAI
This space is built for **model builders, tech enthusiasts, and developers** who want to learn, share, and grow together. Whether you’re just starting out or already deep into AI/ML, you’ll find a supportive community ready to help with knowledge, ideas, and collaboration.
💡 Join us to:
- Connect with fellow developers and AI enthusiasts
- Share your projects, insights, and questions
- Learn from others and contribute to a growing knowledge base
👉 If you’re interested, hop in and be part of the conversation: https://t.me/XenArcAI
We’re excited to introduce our new Telegram group: https://t.me/XenArcAI
This space is built for **model builders, tech enthusiasts, and developers** who want to learn, share, and grow together. Whether you’re just starting out or already deep into AI/ML, you’ll find a supportive community ready to help with knowledge, ideas, and collaboration.
💡 Join us to:
- Connect with fellow developers and AI enthusiasts
- Share your projects, insights, and questions
- Learn from others and contribute to a growing knowledge base
👉 If you’re interested, hop in and be part of the conversation: https://t.me/XenArcAI
-
-
-
- 12 replies
reacted to
their
post with 🔥
about 1 month ago
Post
1639
Another banger from XenArcAI! 🔥
We’re thrilled to unveil three powerful new releases that push the boundaries of AI research and development:
🔗 XenArcAI/SparkEmbedding-300m
- A lightning-fast embedding model built for scale.
- Optimized for semantic search, clustering, and representation learning.
🔗 XenArcAI/CodeX-7M-Non-Thinking
- A massive dataset of 7 million code samples.
- Designed for training models on raw coding patterns without reasoning layers.
🔗 XenArcAI/CodeX-2M-Thinking
- A curated dataset of 2 million code samples.
- Focused on reasoning-driven coding tasks, enabling smarter AI coding assistants.
Together, these projects represent a leap forward in building smarter, faster, and more capable AI systems.
💡 Innovation meets dedication.
🌍 Knowledge meets responsibility.
We’re thrilled to unveil three powerful new releases that push the boundaries of AI research and development:
🔗 XenArcAI/SparkEmbedding-300m
- A lightning-fast embedding model built for scale.
- Optimized for semantic search, clustering, and representation learning.
🔗 XenArcAI/CodeX-7M-Non-Thinking
- A massive dataset of 7 million code samples.
- Designed for training models on raw coding patterns without reasoning layers.
🔗 XenArcAI/CodeX-2M-Thinking
- A curated dataset of 2 million code samples.
- Focused on reasoning-driven coding tasks, enabling smarter AI coding assistants.
Together, these projects represent a leap forward in building smarter, faster, and more capable AI systems.
💡 Innovation meets dedication.
🌍 Knowledge meets responsibility.
posted
an
update
about 1 month ago
Post
1639
Another banger from XenArcAI! 🔥
We’re thrilled to unveil three powerful new releases that push the boundaries of AI research and development:
🔗 XenArcAI/SparkEmbedding-300m
- A lightning-fast embedding model built for scale.
- Optimized for semantic search, clustering, and representation learning.
🔗 XenArcAI/CodeX-7M-Non-Thinking
- A massive dataset of 7 million code samples.
- Designed for training models on raw coding patterns without reasoning layers.
🔗 XenArcAI/CodeX-2M-Thinking
- A curated dataset of 2 million code samples.
- Focused on reasoning-driven coding tasks, enabling smarter AI coding assistants.
Together, these projects represent a leap forward in building smarter, faster, and more capable AI systems.
💡 Innovation meets dedication.
🌍 Knowledge meets responsibility.
We’re thrilled to unveil three powerful new releases that push the boundaries of AI research and development:
🔗 XenArcAI/SparkEmbedding-300m
- A lightning-fast embedding model built for scale.
- Optimized for semantic search, clustering, and representation learning.
🔗 XenArcAI/CodeX-7M-Non-Thinking
- A massive dataset of 7 million code samples.
- Designed for training models on raw coding patterns without reasoning layers.
🔗 XenArcAI/CodeX-2M-Thinking
- A curated dataset of 2 million code samples.
- Focused on reasoning-driven coding tasks, enabling smarter AI coding assistants.
Together, these projects represent a leap forward in building smarter, faster, and more capable AI systems.
💡 Innovation meets dedication.
🌍 Knowledge meets responsibility.
reacted to
their
post with 🔥
about 2 months ago
Post
3041
SparkEmbedding - SoTA cross lingual retrieval
Iam very happy to announce our latest embedding model sparkembedding-300m base on embeddinggemma-300m we fine tuned it on 1m extra examples spanning over 119 languages and result is this model achieves exceptional cross lingual retrieval
Model: XenArcAI/SparkEmbedding-300m
Iam very happy to announce our latest embedding model sparkembedding-300m base on embeddinggemma-300m we fine tuned it on 1m extra examples spanning over 119 languages and result is this model achieves exceptional cross lingual retrieval
Model: XenArcAI/SparkEmbedding-300m
posted
an
update
about 2 months ago
Post
3041
SparkEmbedding - SoTA cross lingual retrieval
Iam very happy to announce our latest embedding model sparkembedding-300m base on embeddinggemma-300m we fine tuned it on 1m extra examples spanning over 119 languages and result is this model achieves exceptional cross lingual retrieval
Model: XenArcAI/SparkEmbedding-300m
Iam very happy to announce our latest embedding model sparkembedding-300m base on embeddinggemma-300m we fine tuned it on 1m extra examples spanning over 119 languages and result is this model achieves exceptional cross lingual retrieval
Model: XenArcAI/SparkEmbedding-300m
reacted to
their
post with 👍
2 months ago
Post
211
AIRealNet - SoTA - Image detection model
We’re proud to release AIRealNet — a binary image classifier built to detect whether an image is AI-generated or a real human photograph. Based on SwinV2 and fine-tuned on the AI-vs-Real dataset, this model is optimized for high-accuracy classification across diverse visual domains.
If you care about synthetic media detection or want to explore the frontier of AI vs human realism, we’d love your support. Please like the model and try it out. Every download helps us improve and expand future versions.
Model page: XenArcAI/AIRealNet
We’re proud to release AIRealNet — a binary image classifier built to detect whether an image is AI-generated or a real human photograph. Based on SwinV2 and fine-tuned on the AI-vs-Real dataset, this model is optimized for high-accuracy classification across diverse visual domains.
If you care about synthetic media detection or want to explore the frontier of AI vs human realism, we’d love your support. Please like the model and try it out. Every download helps us improve and expand future versions.
Model page: XenArcAI/AIRealNet
posted
an
update
3 months ago
Post
211
AIRealNet - SoTA - Image detection model
We’re proud to release AIRealNet — a binary image classifier built to detect whether an image is AI-generated or a real human photograph. Based on SwinV2 and fine-tuned on the AI-vs-Real dataset, this model is optimized for high-accuracy classification across diverse visual domains.
If you care about synthetic media detection or want to explore the frontier of AI vs human realism, we’d love your support. Please like the model and try it out. Every download helps us improve and expand future versions.
Model page: XenArcAI/AIRealNet
We’re proud to release AIRealNet — a binary image classifier built to detect whether an image is AI-generated or a real human photograph. Based on SwinV2 and fine-tuned on the AI-vs-Real dataset, this model is optimized for high-accuracy classification across diverse visual domains.
If you care about synthetic media detection or want to explore the frontier of AI vs human realism, we’d love your support. Please like the model and try it out. Every download helps us improve and expand future versions.
Model page: XenArcAI/AIRealNet
reacted to
their
post with 👍🤗
3 months ago
Post
4493
Ever wanted an open‑source deep research agent? Meet Deepresearch‑Agent 🔍🤖
1. Multi‑step reasoning: Reflects between steps, fills gaps, iterates until evidence is solid.
2. Research‑augmented: Generates queries, searches, synthesizes, and cites sources.
3. Fullstack + LLM‑friendly: React/Tailwind frontend, LangGraph/FastAPI backend; works with OpenAI/Gemini.
🔗 GitHub: https://github.com/Parveshiiii/Deepresearch-Agent
1. Multi‑step reasoning: Reflects between steps, fills gaps, iterates until evidence is solid.
2. Research‑augmented: Generates queries, searches, synthesizes, and cites sources.
3. Fullstack + LLM‑friendly: React/Tailwind frontend, LangGraph/FastAPI backend; works with OpenAI/Gemini.
🔗 GitHub: https://github.com/Parveshiiii/Deepresearch-Agent
posted
an
update
3 months ago
Post
4493
Ever wanted an open‑source deep research agent? Meet Deepresearch‑Agent 🔍🤖
1. Multi‑step reasoning: Reflects between steps, fills gaps, iterates until evidence is solid.
2. Research‑augmented: Generates queries, searches, synthesizes, and cites sources.
3. Fullstack + LLM‑friendly: React/Tailwind frontend, LangGraph/FastAPI backend; works with OpenAI/Gemini.
🔗 GitHub: https://github.com/Parveshiiii/Deepresearch-Agent
1. Multi‑step reasoning: Reflects between steps, fills gaps, iterates until evidence is solid.
2. Research‑augmented: Generates queries, searches, synthesizes, and cites sources.
3. Fullstack + LLM‑friendly: React/Tailwind frontend, LangGraph/FastAPI backend; works with OpenAI/Gemini.
🔗 GitHub: https://github.com/Parveshiiii/Deepresearch-Agent
reacted to
their
post with 🔥
3 months ago
Post
3109
🚀 Big news from XenArcAI!
We’ve just released our new dataset: **Bhagwat‑Gita‑Infinity** 🌸📖
✨ What’s inside:
- Verse‑aligned Sanskrit, Hindi, and English
- Clean, structured, and ready for ML/AI projects
- Perfect for research, education, and open‑source exploration
🔗 Hugging Face: XenArcAI/Bhagwat-Gita-Infinity
Let’s bring timeless wisdom into modern AI together 🙌
We’ve just released our new dataset: **Bhagwat‑Gita‑Infinity** 🌸📖
✨ What’s inside:
- Verse‑aligned Sanskrit, Hindi, and English
- Clean, structured, and ready for ML/AI projects
- Perfect for research, education, and open‑source exploration
🔗 Hugging Face: XenArcAI/Bhagwat-Gita-Infinity
Let’s bring timeless wisdom into modern AI together 🙌
posted
an
update
3 months ago
Post
3109
🚀 Big news from XenArcAI!
We’ve just released our new dataset: **Bhagwat‑Gita‑Infinity** 🌸📖
✨ What’s inside:
- Verse‑aligned Sanskrit, Hindi, and English
- Clean, structured, and ready for ML/AI projects
- Perfect for research, education, and open‑source exploration
🔗 Hugging Face: XenArcAI/Bhagwat-Gita-Infinity
Let’s bring timeless wisdom into modern AI together 🙌
We’ve just released our new dataset: **Bhagwat‑Gita‑Infinity** 🌸📖
✨ What’s inside:
- Verse‑aligned Sanskrit, Hindi, and English
- Clean, structured, and ready for ML/AI projects
- Perfect for research, education, and open‑source exploration
🔗 Hugging Face: XenArcAI/Bhagwat-Gita-Infinity
Let’s bring timeless wisdom into modern AI together 🙌
reacted to
their
post with 🚀🤗
3 months ago
Post
2460
🚀 New Release from XenArcAI
We’re excited to introduce AIRealNet — our SwinV2‑based image classifier built to distinguish between artificial and real images.
✨ Highlights:
- Backbone: SwinV2
- Input size: 256×256
- Labels: artificial vs. real
- Performance: Accuracy 0.999 | F1 0.999 | Val Loss 0.0063
This model is now live on Hugging Face:
👉 XenArcAI/AIRealNet
We built AIRealNet to push forward open‑source tools for authenticity detection, and we can’t wait to see how the community uses it.
We’re excited to introduce AIRealNet — our SwinV2‑based image classifier built to distinguish between artificial and real images.
✨ Highlights:
- Backbone: SwinV2
- Input size: 256×256
- Labels: artificial vs. real
- Performance: Accuracy 0.999 | F1 0.999 | Val Loss 0.0063
This model is now live on Hugging Face:
👉 XenArcAI/AIRealNet
We built AIRealNet to push forward open‑source tools for authenticity detection, and we can’t wait to see how the community uses it.
posted
an
update
3 months ago
Post
2460
🚀 New Release from XenArcAI
We’re excited to introduce AIRealNet — our SwinV2‑based image classifier built to distinguish between artificial and real images.
✨ Highlights:
- Backbone: SwinV2
- Input size: 256×256
- Labels: artificial vs. real
- Performance: Accuracy 0.999 | F1 0.999 | Val Loss 0.0063
This model is now live on Hugging Face:
👉 XenArcAI/AIRealNet
We built AIRealNet to push forward open‑source tools for authenticity detection, and we can’t wait to see how the community uses it.
We’re excited to introduce AIRealNet — our SwinV2‑based image classifier built to distinguish between artificial and real images.
✨ Highlights:
- Backbone: SwinV2
- Input size: 256×256
- Labels: artificial vs. real
- Performance: Accuracy 0.999 | F1 0.999 | Val Loss 0.0063
This model is now live on Hugging Face:
👉 XenArcAI/AIRealNet
We built AIRealNet to push forward open‑source tools for authenticity detection, and we can’t wait to see how the community uses it.