Phi 3.5 Vision
🔥
5
Analyze artwork and answer questions about images
Gizem PRO
gizemsarsinlar
AI & ML interests
None yet
Recent Activity
updated
a Space 22 days ago
gizemsarsinlar/Phi-3.5-Artwork-Analysis updated
a Space 9 months ago
Agents-MCP-Hackathon/Art-Historian-AI updated
a Space 9 months ago
gizemsarsinlar/Art-Historian-AI Organizations
updated a Space 22 days ago
updated 2 Spaces 9 months ago
published 2 Spaces 9 months ago
liked a Space 9 months ago
published a Space 11 months ago
updated a Space 11 months ago
liked 2 Spaces about 1 year ago
updated a Space about 1 year ago
liked 2 Spaces about 1 year ago
updated a Space over 1 year ago
liked 2 models over 1 year ago
reacted to merve's post with 🔥 over 1 year ago
Post
2761
NVIDIA just dropped a gigantic multimodal model called NVLM 72B 🦖
nvidia/NVLM-D-72B
Paper page NVLM: Open Frontier-Class Multimodal LLMs (2409.11402)
The paper contains many ablation studies on various ways to use the LLM backbone 👇🏻
🦩 Flamingo-like cross-attention (NVLM-X)
🌋 Llava-like concatenation of image and text embeddings to a decoder-only model (NVLM-D)
✨ a hybrid architecture (NVLM-H)
Checking evaluations, NVLM-D and NVLM-H are best or second best compared to other models 👏
The released model is NVLM-D based on Qwen-2 Instruct, aligned with InternViT-6B using a huge mixture of different datasets
You can easily use this model by loading it through transformers' AutoModel 😍
nvidia/NVLM-D-72B
Paper page NVLM: Open Frontier-Class Multimodal LLMs (2409.11402)
The paper contains many ablation studies on various ways to use the LLM backbone 👇🏻
🦩 Flamingo-like cross-attention (NVLM-X)
🌋 Llava-like concatenation of image and text embeddings to a decoder-only model (NVLM-D)
✨ a hybrid architecture (NVLM-H)
Checking evaluations, NVLM-D and NVLM-H are best or second best compared to other models 👏
The released model is NVLM-D based on Qwen-2 Instruct, aligned with InternViT-6B using a huge mixture of different datasets
You can easily use this model by loading it through transformers' AutoModel 😍
reacted to merve's post with 👍 over 1 year ago
Post
4062
If you feel like you missed out for ECCV 2024, there's an app to browse the papers, rank for popularity, filter for open models, datasets and demos 📝
Get started at https://huggingface.co/spaces/ECCV/ECCV2024-papers ✨
Get started at https://huggingface.co/spaces/ECCV/ECCV2024-papers ✨
liked 2 Spaces over 1 year ago