microsoft/Phi-4-multimodal-instruct-onnx
Automatic Speech Recognition
β’
Updated
β’
481
β’
39
Victor Mustar PRO
victor
AI & ML interests
Building the UX of this website
Recent Activity
liked
a model
about 4 hours ago
microsoft/Phi-4-multimodal-instruct-onnx
liked
a model
about 4 hours ago
microsoft/Phi-4-multimodal-instruct
reacted
to
rizavelioglu's
post
with β€οΈ
about 4 hours ago
Comparing reconstruction quality of various VAEs with an interactive demo
https://huggingface.co/spaces/rizavelioglu/vae-comparison
Organizations
victor's activity
liked
2
models
about 4 hours ago
reacted to
rizavelioglu's
post with β€οΈ
about 4 hours ago
Post
2036
Comparing reconstruction quality of various VAEs with an interactive demo
rizavelioglu/vae-comparison
rizavelioglu/vae-comparison
- 1 reply
reacted to
mkurman's
post with β€οΈ
about 4 hours ago
Post
3134
Introducing a new architecture, MedIT One β a single-token transformer with LSTM-like recurrence.
It is extremely fast in training and inference, but we lack funding for large-scale training. Enjoy π
https://github.com/MedITSolutionsKurman/medit-one
It is extremely fast in training and inference, but we lack funding for large-scale training. Enjoy π
https://github.com/MedITSolutionsKurman/medit-one
reacted to
singhsidhukuldeep's
post with π
about 4 hours ago
Post
2528
Exciting New Tool for Knowledge Graph Extraction from Plain Text!
I just came across a groundbreaking new tool called KGGen that's solving a major challenge in the AI world - the scarcity of high-quality knowledge graph data.
KGGen is an open-source Python package that leverages language models to extract knowledge graphs (KGs) from plain text. What makes it special is its innovative approach to clustering related entities, which significantly reduces sparsity in the extracted KGs.
The technical approach is fascinating:
1. KGGen uses a multi-stage process involving an LLM (GPT-4o in their implementation) to extract entities and relations from source text
2. It aggregates graphs across sources to reduce redundancy
3. Most importantly, it applies iterative LM-based clustering to refine the raw graph
The clustering stage is particularly innovative - it identifies which nodes and edges refer to the same underlying entities or concepts. This normalizes variations in tense, plurality, stemming, and capitalization (e.g., "labors" clustered with "labor").
The researchers from Stanford and University of Toronto also introduced MINE (Measure of Information in Nodes and Edges), the first benchmark for evaluating KG extractors. When tested against existing methods like OpenIE and GraphRAG, KGGen outperformed them by up to 18%.
For anyone working with knowledge graphs, RAG systems, or KG embeddings, this tool addresses the fundamental challenge of data scarcity that's been holding back progress in graph-based foundation models.
The package is available via pip install kg-gen, making it accessible to everyone. This could be a game-changer for knowledge graph applications!
I just came across a groundbreaking new tool called KGGen that's solving a major challenge in the AI world - the scarcity of high-quality knowledge graph data.
KGGen is an open-source Python package that leverages language models to extract knowledge graphs (KGs) from plain text. What makes it special is its innovative approach to clustering related entities, which significantly reduces sparsity in the extracted KGs.
The technical approach is fascinating:
1. KGGen uses a multi-stage process involving an LLM (GPT-4o in their implementation) to extract entities and relations from source text
2. It aggregates graphs across sources to reduce redundancy
3. Most importantly, it applies iterative LM-based clustering to refine the raw graph
The clustering stage is particularly innovative - it identifies which nodes and edges refer to the same underlying entities or concepts. This normalizes variations in tense, plurality, stemming, and capitalization (e.g., "labors" clustered with "labor").
The researchers from Stanford and University of Toronto also introduced MINE (Measure of Information in Nodes and Edges), the first benchmark for evaluating KG extractors. When tested against existing methods like OpenIE and GraphRAG, KGGen outperformed them by up to 18%.
For anyone working with knowledge graphs, RAG systems, or KG embeddings, this tool addresses the fundamental challenge of data scarcity that's been holding back progress in graph-based foundation models.
The package is available via pip install kg-gen, making it accessible to everyone. This could be a game-changer for knowledge graph applications!
reacted to
Jaward's
post with π€
about 4 hours ago
Post
4454
made a few improvements on custom grpo trainer:
- added sequence similarity reward (seems to work)
- improved vllm support (5x inference speed)
- adjusted reward scores (this helped with format/accuracy)
- can now push to hf hub (already pushed mine lol: Jaward/smollm2_360m_grpo_gsm8k_reasoner)
Code: https://github.com/Jaykef/ai-algorithms/blob/main/smollm2_360M_135M_grpo_gsm8k.ipynb
- added sequence similarity reward (seems to work)
- improved vllm support (5x inference speed)
- adjusted reward scores (this helped with format/accuracy)
- can now push to hf hub (already pushed mine lol: Jaward/smollm2_360m_grpo_gsm8k_reasoner)
Code: https://github.com/Jaykef/ai-algorithms/blob/main/smollm2_360M_135M_grpo_gsm8k.ipynb
reacted to
Kseniase's
post with π₯
about 4 hours ago
Post
3105
9 types of "Chain-of-..." approaches:
Chain-of-Thought (CoT) prompting enhances reasoning in AI models by breaking down complex problems into step-by-step logical sequences. It continues proving its effectiveness, especially in top-performing reasoning models. However, there are other similar methods, that expand CoT and can be used for different purposes. Here are 9 of them:
1. Chain-of-Action-Thought (COAT) -> Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search (2502.02508)
Helps model decide when to keep thinking, double-check their work, or try a different approach, using special guiding tokens.
2. Chain of Draft (CoD) -> Chain of Draft: Thinking Faster by Writing Less (2502.18600)
It helps model generate short but meaningful reasoning steps, cutting costs and making processing faster
3. Chain-of-Agents -> Chain of Agents: Large Language Models Collaborating on Long-Context Tasks (2406.02818)
Uses multi-agent collaboration: Worker agents process text parts in a structured chain, and manager agent summarizes the results
4. Chain-of-RAG ->https://huggingface.co/papers/2501.14342
Creates retrieval chains, instead of retrieving all info at once. It can dynamically adjust its search process and its parameters like step number
5. Chain-of-Shot Prompting (CoS) -> CoS: Chain-of-Shot Prompting for Long Video Understanding (2502.06428)
Helps models pick frames crucial for understanding a video, using a binary video summary and video co-reasoning module.
6. Chain of Hindsight (CoH) -> Chain of Hindsight Aligns Language Models with Feedback (2302.02676)
Converts all feedback into sequences to fine-tune the model and refine outputs
7. Chain-of-Note (CoN) -> Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models (2311.09210)
Generates sequential reading notes for each retrieved document to assess relevance before integrating info into the final answer
8. Chain of Diagnosis (CoD) -> CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis (2407.13301)
Transforms the diagnostic process into a diagnostic chain
9. Chain(s)-of-Knowledge -> https://www.turingpost.com/p/cok
Enhance LLMs by dynamically pulling in external knowledge to improve accuracy and reduce errors
Chain-of-Thought (CoT) prompting enhances reasoning in AI models by breaking down complex problems into step-by-step logical sequences. It continues proving its effectiveness, especially in top-performing reasoning models. However, there are other similar methods, that expand CoT and can be used for different purposes. Here are 9 of them:
1. Chain-of-Action-Thought (COAT) -> Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search (2502.02508)
Helps model decide when to keep thinking, double-check their work, or try a different approach, using special guiding tokens.
2. Chain of Draft (CoD) -> Chain of Draft: Thinking Faster by Writing Less (2502.18600)
It helps model generate short but meaningful reasoning steps, cutting costs and making processing faster
3. Chain-of-Agents -> Chain of Agents: Large Language Models Collaborating on Long-Context Tasks (2406.02818)
Uses multi-agent collaboration: Worker agents process text parts in a structured chain, and manager agent summarizes the results
4. Chain-of-RAG ->https://huggingface.co/papers/2501.14342
Creates retrieval chains, instead of retrieving all info at once. It can dynamically adjust its search process and its parameters like step number
5. Chain-of-Shot Prompting (CoS) -> CoS: Chain-of-Shot Prompting for Long Video Understanding (2502.06428)
Helps models pick frames crucial for understanding a video, using a binary video summary and video co-reasoning module.
6. Chain of Hindsight (CoH) -> Chain of Hindsight Aligns Language Models with Feedback (2302.02676)
Converts all feedback into sequences to fine-tune the model and refine outputs
7. Chain-of-Note (CoN) -> Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models (2311.09210)
Generates sequential reading notes for each retrieved document to assess relevance before integrating info into the final answer
8. Chain of Diagnosis (CoD) -> CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis (2407.13301)
Transforms the diagnostic process into a diagnostic chain
9. Chain(s)-of-Knowledge -> https://www.turingpost.com/p/cok
Enhance LLMs by dynamically pulling in external knowledge to improve accuracy and reduce errors
reacted to
MohamedRashad's
post with β€οΈ
about 4 hours ago
Post
900
I think we have released the best Arabic model under 25B at least based on
inceptionai/AraGen-Leaderboard
Yehia = ALLaM-AI/ALLaM-7B-Instruct-preview + GRPO
and its ranked number one model under the 25B parameter size mark.
Now, i said "i think" not "i am sure" because this model used the same metric of evaluation the AraGen developers use (the 3C3H) as a reward model to improve its responses and this sparks the question. Is this something good for users or is it another type of overfitting that we don't want ?
I don't know if this is a good thing or a bad thing but what i know is that you can try it from here:
Navid-AI/Yehia-7B-preview
or Download it for your personal experiments from here:
Navid-AI/Yehia-7B-preview
Ramada Kareem π
Yehia = ALLaM-AI/ALLaM-7B-Instruct-preview + GRPO
and its ranked number one model under the 25B parameter size mark.
Now, i said "i think" not "i am sure" because this model used the same metric of evaluation the AraGen developers use (the 3C3H) as a reward model to improve its responses and this sparks the question. Is this something good for users or is it another type of overfitting that we don't want ?
I don't know if this is a good thing or a bad thing but what i know is that you can try it from here:
Navid-AI/Yehia-7B-preview
or Download it for your personal experiments from here:
Navid-AI/Yehia-7B-preview
Ramada Kareem π
reacted to
elismasilva's
post with π₯
about 4 hours ago
Post
251
MoD ControlNet Tile Upscaler for SDXL: Upscale Your Images with Ease! π
Meet the MoD ControlNet Tile Upscaler for SDXL, a powerful tool that uses advanced technology to upscale your images without losing quality! Our app is designed to process images in tiles without leaving them blurry or with visible lines between the tiles. The result? Upscaled images with preserved details and smooth, natural transitionsβall through a user-friendly interface. β¨
What MoD Upscaler Offers:
π Preserved Details: Unlike traditional upscalers, the MoD ControlNet Tile Upscaler enlarges your images while maintaining clarity and adding details that might otherwise be lost. Your photos gain more definition without sacrificing original quality.
𧩠Advanced Tiling Technology: We use a smart combination of techniques to ensure natural and smooth transitions between tiles. This means your upscaled images remain consistent and high-quality, even at higher resolutions. No more visible lines or imperfections!
β‘ Fast and Efficient: You donβt need a super-powered computer! Our app is optimized to run quickly and smoothly, even on simpler machines.
π¨ Easy-to-Use Interface: You donβt have to be an expert to use the MoD ControlNet Tile Upscaler. The interface is simple, intuitive, and designed so anyone can achieve professional-quality results without hassle.
Upscale your images without losing quality and with details preserved. Try the MoD ControlNet Tile Upscaler today! π
Demo App: elismasilva/mod-control-tile-upscaler-sdxl
Github Code: https://github.com/DEVAIEXP/mod-control-tile-upscaler-sdxl
We use Gradio amazing interfaces.
We use Hugging Face Diffusers to build this tool and Hugging Face Spaces to run this demo.
Thank you all! π
Meet the MoD ControlNet Tile Upscaler for SDXL, a powerful tool that uses advanced technology to upscale your images without losing quality! Our app is designed to process images in tiles without leaving them blurry or with visible lines between the tiles. The result? Upscaled images with preserved details and smooth, natural transitionsβall through a user-friendly interface. β¨
What MoD Upscaler Offers:
π Preserved Details: Unlike traditional upscalers, the MoD ControlNet Tile Upscaler enlarges your images while maintaining clarity and adding details that might otherwise be lost. Your photos gain more definition without sacrificing original quality.
𧩠Advanced Tiling Technology: We use a smart combination of techniques to ensure natural and smooth transitions between tiles. This means your upscaled images remain consistent and high-quality, even at higher resolutions. No more visible lines or imperfections!
β‘ Fast and Efficient: You donβt need a super-powered computer! Our app is optimized to run quickly and smoothly, even on simpler machines.
π¨ Easy-to-Use Interface: You donβt have to be an expert to use the MoD ControlNet Tile Upscaler. The interface is simple, intuitive, and designed so anyone can achieve professional-quality results without hassle.
Upscale your images without losing quality and with details preserved. Try the MoD ControlNet Tile Upscaler today! π
Demo App: elismasilva/mod-control-tile-upscaler-sdxl
Github Code: https://github.com/DEVAIEXP/mod-control-tile-upscaler-sdxl
We use Gradio amazing interfaces.
We use Hugging Face Diffusers to build this tool and Hugging Face Spaces to run this demo.
Thank you all! π
liked
a
Space
about 4 hours ago
[FEEDBACK] Notifications
141
#6 opened over 2 years ago
by
victor
upvoted
a
paper
about 10 hours ago
liked
a
Space
about 12 hours ago
liked
a
model
about 12 hours ago
liked
6
Spaces
about 12 hours ago
22
Pdf To Structured Data
π
PDF to Structured Data powered by Google DeepMind Gemini 2.0
12
Moonshine Live Transcription
π
Real-time captions with Moonshine ONNX
21
Phi 4 Multimodal
π
Interact with a multimodal AI model using text, images, and audio
14
HandSpew
π
Generate thoughts based on hand gestures
9
Magma Gaming
π¦
Magma playing video games
7
vggt
π
vggt (alpha test)