LLM Models · Open Source
Browse the world's large language models. Compare parameters, benchmarks, VRAM and more.
Gemma 2 Baku 2B Instruct (rinna/gemma-2-baku-2b-it)
UI-TARS-72B-SFT UI-TARS-2B-SFT UI-TARS-7B-SFT UI-TARS-7B-DPO (Recommended) UI-TARS-72B-SFT UI-TARS-72B-DPO (Recommended) Introduction
Qwen-SEA-LION-v4-32B-IT-4BIT (GPTQ model)
💻Github Repo • 🤗Model Collections • 📜Technical Report • 💬Online Chat
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…
This is the model is trained using paper, M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models.
Gemma-2-Llama-Swallow series was built by continual pre-training on the gemma-2 models. Gemma 2 Swallow enhanced the Japanese language capabilities of the original Gemma 2 while retaining the English language capabilities. We use approximately 200 billion tokens that were sampled…
We introduce an updated version of LongCat-Flash-Thinking, named LongCat-Flash-Thinking-2601, a powerful and efficient Large Reasoning Model (LRM) with 560 billion total parameters, built upon an innovative Mixture-of-Experts (MoE) architecture.
python from transformers import pipeline
[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.
- Arxiv - Github - Model Collection - Data
Llama 3 Youko 8B (rinna/llama-3-youko-8b)