LLM Models · Multimodal
Browse the world's large language models. Compare parameters, benchmarks, VRAM and more.
Reinforcement learning (RL) (e.g., GRPO) helps with grounding because of its inherent objective alignment—rewarding successful clicks—rather than encouraging long textual Chain-of-Thought (CoT) reasoning. Unlike approaches that rely heavily on verbose CoT reasoning, GRPO directly…
CapRL 📖 Paper 🏠 Github 🤗 CapRL Collection 🤗 Daily Paper
Bunny is a family of lightweight but powerful multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Llama-3-8B, Phi-1.5, StableLM-2, Qwen1.5, MiniCPM and Phi-2. To compensate for the decrease in model size, we…
Penguin-VL Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
💻Github Repo • 🤗HF Model Collections • 🤖ModelScope Collections • 💬Online Chat
Penguin-VL Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Falcon2-11B-vlm is an 11B parameters causal decoder-only model built by TII and trained on over 5,000B tokens of RefinedWeb enhanced with curated corpora. To bring vision capabilities, we integrate the pretrained CLIP ViT-L/14 vision encoder with our Falcon2-11B chat-finetuned mo…
📖 Paper 🏠 Github 🤗 Spatial-SSRL-7B Model 🤗 Spatial-SSRL-3B Model 🤗 Spatial-SSRL-Qwen3VL-4B Model 🤗 Spatial-SSRL-81k Dataset 📰 Daily Paper
We also provide v1.1 version accepting high-resolution images up to 1152x1152. 🤗 v1.1
[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.