takara-ai/rand-1m-multimodal
Viewer
β’
Updated
β’
1M
β’
32
takara.ai
company
Verified
AI & ML interests
GenAI, Diffusion, LLM's and State of the Art Solutions.
Recent Activity
takara-ai's activity
takarajordanΒ
published
a
dataset
9 days ago
takarajordanΒ
updated
a
dataset
12 days ago
takarajordanΒ
published
a
dataset
12 days ago
takarajordanΒ
posted
an
update
29 days ago
Post
594
π Two months in, https://github.com/takara-ai/go-attention has passed 429 stars on GitHub.
We built this library at takara.ai to bring attention mechanisms and transformer layers to Go β in a form that's lightweight, clean, and dependency-free.
Weβre proud to say that every part of this project reflects what we set out to do.
- Pure Go β no external dependencies, built entirely on the Go standard library
- Core support for DotProductAttention and MultiHeadAttention
- Full transformer layers with LayerNorm, feed-forward networks, and residual connections
- Designed for edge, embedded, and real-time environments where simplicity and performance matter
Thank you to everyone who has supported this so far β the stars, forks, and feedback mean a lot.
We built this library at takara.ai to bring attention mechanisms and transformer layers to Go β in a form that's lightweight, clean, and dependency-free.
Weβre proud to say that every part of this project reflects what we set out to do.
- Pure Go β no external dependencies, built entirely on the Go standard library
- Core support for DotProductAttention and MultiHeadAttention
- Full transformer layers with LayerNorm, feed-forward networks, and residual connections
- Designed for edge, embedded, and real-time environments where simplicity and performance matter
Thank you to everyone who has supported this so far β the stars, forks, and feedback mean a lot.
-
- 4 replies
takarajordanΒ
posted
an
update
about 1 month ago
Post
1577
AI research over coffee βοΈ
No abstracts, just bullet points.
Start your day here: https://tldr.takara.ai
No abstracts, just bullet points.
Start your day here: https://tldr.takara.ai
- 1 reply
takarajordanΒ
updated
a
collection
about 1 month ago
takarajordanΒ
posted
an
update
about 1 month ago
Post
1867
Takara takes 3rd place in the {tech:munich} AI hackathon with Fudeno!
A little over 2 weeks ago @aldigobbler and I set out to create the largest MultiModal SVG dataset ever created, we succeeded in this and when I was in Munich, Germany I took it one step further and made an entire app with it!
We fine-tuned Mistral Small, made a Next.JS application and blew some minds, taking 3rd place out of over 100 hackers. So cool!
If you want to see the dataset, please see below.
takara-ai/fudeno-instruct-4M
A little over 2 weeks ago @aldigobbler and I set out to create the largest MultiModal SVG dataset ever created, we succeeded in this and when I was in Munich, Germany I took it one step further and made an entire app with it!
We fine-tuned Mistral Small, made a Next.JS application and blew some minds, taking 3rd place out of over 100 hackers. So cool!
If you want to see the dataset, please see below.
takara-ai/fudeno-instruct-4M
takarajordanΒ
updated
a
dataset
about 2 months ago
takarajordanΒ
published
a
dataset
about 2 months ago
Post
2489
πAraClip is now fully integrated with Hugging Face π€
AraClip is a specialized CLIP model that was created by @pain and optimized for Arabic text-image retrieval tasksπ₯
π Try it out π
π€ model: Arabic-Clip/araclip
𧩠Gradio demo: Arabic-Clip/Araclip-Simplified
π website: https://arabic-clip.github.io/Arabic-CLIP/
AraClip is a specialized CLIP model that was created by @pain and optimized for Arabic text-image retrieval tasksπ₯
π Try it out π
π€ model: Arabic-Clip/araclip
𧩠Gradio demo: Arabic-Clip/Araclip-Simplified
π website: https://arabic-clip.github.io/Arabic-CLIP/
- 2 replies
takarajordanΒ
updated
a
dataset
about 2 months ago
takarajordanΒ
updated
a
dataset
2 months ago
takarajordanΒ
published
a
dataset
2 months ago
Post
1439
ππ»ββοΈHey there folks,
Did you know that you can use ModernBERT to detect model hallucinations ?
Check out the Demo : Tonic/hallucination-test
See here for Medical Context Demo : MultiTransformer/tonic-discharge-guard
check out the model from KRLabs : KRLabsOrg/lettucedect-large-modernbert-en-v1
and the library they kindly open sourced for it : https://github.com/KRLabsOrg/LettuceDetect
ππ»if you like this topic please contribute code upstream π
Did you know that you can use ModernBERT to detect model hallucinations ?
Check out the Demo : Tonic/hallucination-test
See here for Medical Context Demo : MultiTransformer/tonic-discharge-guard
check out the model from KRLabs : KRLabsOrg/lettucedect-large-modernbert-en-v1
and the library they kindly open sourced for it : https://github.com/KRLabsOrg/LettuceDetect
ππ»if you like this topic please contribute code upstream π
- 2 replies
Post
787
Powered by
KRLabsOrg/lettucedect-large-modernbert-en-v1 from KRLabsOrg.
Detect hallucinations in answers based on context and questions using ModernBERT with 8192-token context support!
### Model Details
- **Model Name**: [lettucedect-large-modernbert-en-v1]( KRLabsOrg/lettucedect-large-modernbert-en-v1)
- **Organization**: [KRLabsOrg](
KRLabsOrg
)
- **Github**: [https://github.com/KRLabsOrg/LettuceDetect](https://github.com/KRLabsOrg/LettuceDetect)
- **Architecture**: ModernBERT (Large) with extended context support up to 8192 tokens
- **Task**: Token Classification / Hallucination Detection
- **Training Dataset**: [RagTruth]( wandb/RAGTruth-processed)
- **Language**: English
- **Capabilities**: Detects hallucinated spans in answers, provides confidence scores, and calculates average confidence across detected spans.
LettuceDetect excels at processing long documents to determine if an answer aligns with the provided context, making it a powerful tool for ensuring factual accuracy.
Detect hallucinations in answers based on context and questions using ModernBERT with 8192-token context support!
### Model Details
- **Model Name**: [lettucedect-large-modernbert-en-v1]( KRLabsOrg/lettucedect-large-modernbert-en-v1)
- **Organization**: [KRLabsOrg](
KRLabsOrg
) - **Github**: [https://github.com/KRLabsOrg/LettuceDetect](https://github.com/KRLabsOrg/LettuceDetect)
- **Architecture**: ModernBERT (Large) with extended context support up to 8192 tokens
- **Task**: Token Classification / Hallucination Detection
- **Training Dataset**: [RagTruth]( wandb/RAGTruth-processed)
- **Language**: English
- **Capabilities**: Detects hallucinated spans in answers, provides confidence scores, and calculates average confidence across detected spans.
LettuceDetect excels at processing long documents to determine if an answer aligns with the provided context, making it a powerful tool for ensuring factual accuracy.
takarajordanΒ
updated
a
dataset
2 months ago
takarajordanΒ
updated
a
model
2 months ago
takarajordanΒ
updated
a
dataset
2 months ago
takarajordanΒ
updated
a
model
2 months ago