LLM Models
Browse the world's large language models. Compare parameters, benchmarks, VRAM and more.
InstructBLIP model using Vicuna-13b as language model. InstructBLIP was introduced in the paper InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning by Dai et al.
--- inference: false language: - en tags: - instruction-finetuning pretty name: JudgeLM-100K task categories: - text-generation ---
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
A 15B-parameter token-mixer supernet with 8 optimized deployment presets spanning 1.0× to 10.7× decode throughput at 32K sequence length, all from a single checkpoint. Derived from Apriel-1.6 through stochastic distillation and targeted supervised fine-tuning.
--- inference: false language: - en tags: - instruction-finetuning pretty name: JudgeLM-100K task categories: - text-generation ---
Towards a Recursively Self-Improving Agent for Deep Research
CapRL 📖 Paper 🏠 Github 🤗 CapRL Collection 🤗 Daily Paper
📖 Paper 🏠 Github 🤗 Spatial-SSRL-7B Model 🤗 Spatial-SSRL-3B Model 🤗 Spatial-SSRL-Qwen3VL-4B Model 🤗 Spatial-SSRL-81k Dataset 📰 Daily Paper
0. TL;DR 1. Model Details 2. Training Details 3. Usage 4. Evaluation 5. Citation
This repository provides Japanese language models trained by SB Intuitions.
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…