ucsahin/TR-Visual-Docs
Viewer
β’
Updated
β’
4
Umitcan Sahin PRO
ucsahin
AI & ML interests
Visual Language Models, Large Language Models, Vision Transformers
Recent Activity
new activity
about 12 hours ago
ucsahin/TR-Visual-Docs:[bot] Conversion to Parquet
published
a dataset
about 12 hours ago
ucsahin/TR-Visual-Docs
liked
a model
about 14 hours ago
microsoft/Phi-4-multimodal-instruct
Organizations
None yet
ucsahin's activity
[bot] Conversion to Parquet
#1 opened 3 months ago
by
parquet-converter
published
a
dataset
about 12 hours ago
liked
a
model
about 14 hours ago
liked
a
model
4 days ago
liked
a
model
5 days ago
reacted to
merve's
post with π
8 days ago
Post
5148
Google just released PaliGemma 2 Mix: new versatile instruction vision language models π₯
> Three new models: 3B, 10B, 28B with res 224, 448 π
> Can do vision language tasks with open-ended prompts, understand documents, and segment or detect anything π€―
Read more https://huggingface.co./blog/paligemma2mix
Try the demo google/paligemma2-10b-mix
All models are here google/paligemma-2-mix-67ac6a251aaf3ee73679dcc4
> Three new models: 3B, 10B, 28B with res 224, 448 π
> Can do vision language tasks with open-ended prompts, understand documents, and segment or detect anything π€―
Read more https://huggingface.co./blog/paligemma2mix
Try the demo google/paligemma2-10b-mix
All models are here google/paligemma-2-mix-67ac6a251aaf3ee73679dcc4
reacted to
davanstrien's
post with π
29 days ago
Post
1914
Updated the ColPali Query Generator Space
davanstrien/ColPali-Query-Generator to use
Qwen/Qwen2.5-VL-7B-Instruct.
Given an input image, it generates several queries along with explanations to justify them. This approach can generate synthetic data for fine-tuning ColPali models.
Given an input image, it generates several queries along with explanations to justify them. This approach can generate synthetic data for fine-tuning ColPali models.
liked
3
models
about 1 month ago
reacted to
merve's
post with π₯
about 1 month ago
Post
5208
Oof, what a week! π₯΅ So many things have happened, let's recap!
merve/jan-24-releases-6793d610774073328eac67a9
Multimodal π¬
- We have released SmolVLM -- tiniest VLMs that come in 256M and 500M, with it's retrieval models ColSmol for multimodal RAG π
- UI-TARS are new models by ByteDance to unlock agentic GUI control π€― in 2B, 7B and 72B
- Alibaba DAMO lab released VideoLlama3, new video LMs that come in 2B and 7B
- MiniMaxAI released Minimax-VL-01, where decoder is based on MiniMax-Text-01 456B MoE model with long context
- Dataset: Yale released a new benchmark called MMVU
- Dataset: CAIS released Humanity's Last Exam (HLE) a new challenging MM benchmark
LLMs π
- DeepSeek-R1 & DeepSeek-R1-Zero: gigantic 660B reasoning models by DeepSeek, and six distilled dense models, on par with o1 with MIT license! π€―
- Qwen2.5-Math-PRM: new math models by Qwen in 7B and 72B
- NVIDIA released AceMath and AceInstruct, new family of models and their datasets (SFT and reward ones too!)
Audio π£οΈ
- Llasa is a new speech synthesis model based on Llama that comes in 1B,3B, and 8B
- TangoFlux is a new audio generation model trained from scratch and aligned with CRPO
Image/Video/3D Generation β―οΈ
- Flex.1-alpha is a new 8B pre-trained diffusion model by ostris similar to Flux
- tencent released Hunyuan3D-2, new 3D asset generation from images
Multimodal π¬
- We have released SmolVLM -- tiniest VLMs that come in 256M and 500M, with it's retrieval models ColSmol for multimodal RAG π
- UI-TARS are new models by ByteDance to unlock agentic GUI control π€― in 2B, 7B and 72B
- Alibaba DAMO lab released VideoLlama3, new video LMs that come in 2B and 7B
- MiniMaxAI released Minimax-VL-01, where decoder is based on MiniMax-Text-01 456B MoE model with long context
- Dataset: Yale released a new benchmark called MMVU
- Dataset: CAIS released Humanity's Last Exam (HLE) a new challenging MM benchmark
LLMs π
- DeepSeek-R1 & DeepSeek-R1-Zero: gigantic 660B reasoning models by DeepSeek, and six distilled dense models, on par with o1 with MIT license! π€―
- Qwen2.5-Math-PRM: new math models by Qwen in 7B and 72B
- NVIDIA released AceMath and AceInstruct, new family of models and their datasets (SFT and reward ones too!)
Audio π£οΈ
- Llasa is a new speech synthesis model based on Llama that comes in 1B,3B, and 8B
- TangoFlux is a new audio generation model trained from scratch and aligned with CRPO
Image/Video/3D Generation β―οΈ
- Flex.1-alpha is a new 8B pre-trained diffusion model by ostris similar to Flux
- tencent released Hunyuan3D-2, new 3D asset generation from images
- 7 replies
liked
a
model
about 1 month ago
upvoted
a
collection
about 1 month ago
liked
2
models
about 1 month ago
reacted to
kadirnar's
post with ππ₯
about 1 month ago
Post
2963
I created my own AI image and video from scratch using the fal.ai platform π«
Workflow: Flux Lora Training + Upscale + Kling AI(1.6)
Workflow: Flux Lora Training + Upscale + Kling AI(1.6)
- 5 replies
liked
2
models
about 1 month ago
reacted to
fdaudens's
post with π
about 2 months ago
Post
2328
π₯ The AI Agent hype is real! This blog post deep dives into everything you need to know before deploying them: from key definitions to practical recommendations. A must-read for anyone building the future of autonomous systems.
π Key insight: A clear table breaking down the 5 levels of AI agents - from simple processors to fully autonomous systems. Essential framework for understanding where your agent stands on the autonomy spectrum
βοΈ Deep analysis of 15 core values reveals critical trade-offs: accuracy, privacy, safety, equity & more. The same features that make agents powerful can make them risky. Understanding these trade-offs is crucial for responsible deployment
π― 6 key recommendations for the road ahead:
- Create rigorous evaluation protocols
- Study societal effects
- Understand ripple effects
- Improve transparency
- Open source can make a positive difference
- Monitor base model evolution
Read the blog post: https://huggingface.co./blog/ethics-soc-7 Brillant work by @meg @evijit @sasha @giadap
π Key insight: A clear table breaking down the 5 levels of AI agents - from simple processors to fully autonomous systems. Essential framework for understanding where your agent stands on the autonomy spectrum
βοΈ Deep analysis of 15 core values reveals critical trade-offs: accuracy, privacy, safety, equity & more. The same features that make agents powerful can make them risky. Understanding these trade-offs is crucial for responsible deployment
π― 6 key recommendations for the road ahead:
- Create rigorous evaluation protocols
- Study societal effects
- Understand ripple effects
- Improve transparency
- Open source can make a positive difference
- Monitor base model evolution
Read the blog post: https://huggingface.co./blog/ethics-soc-7 Brillant work by @meg @evijit @sasha @giadap