SPEAR Models of the SPEAR series. INSAIT-Institute/spear1-franka Visual Question Answering • 4B • Updated 26 days ago • 102 • 5
MamayLM-v1.0-Gemma-3 First Open and Multimodal Ukrainian-focused LLM INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v1.0 Image-Text-to-Text • 12B • Updated Sep 27 • 1.09k • 14 Running 18 18 MamayLM v1.0 Release Blog 🌻 MamayLM v1.0 - now multimodal and even stronger! INSAIT-Institute/MamayLM-Gemma-3-4B-IT-v1.0 Image-Text-to-Text • 4B • Updated Sep 27 • 490 • 9 INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v1.0-GGUF 12B • Updated Sep 9 • 650 • 12
MixAT A model collection consisting of different model adapters trained with our adversarial training method MixAT MixAT: Combining Continuous and Discrete Adversarial Training for LLMs Paper • 2505.16947 • Published May 22 INSAIT-Institute/Qwen-32B-MixAT Updated Jun 9 • 11 INSAIT-Institute/Qwen-14B-MixAT Updated Jun 9 • 7 INSAIT-Institute/Qwen-14B-MixAT-GCG Updated Jun 9 • 4
MixAT: Combining Continuous and Discrete Adversarial Training for LLMs Paper • 2505.16947 • Published May 22
MamayLM-Gemma-2 Ukrainian-focused MamayLM model collection, based on Gemma2 INSAIT-Institute/MamayLM-Gemma-2-9B-IT-v0.1 Text Generation • 9B • Updated Jun 17 • 683 • • 25 INSAIT-Institute/MamayLM-Gemma-2-9B-IT-v0.1-GGUF 9B • Updated Apr 22 • 406 • 13
ReVLA: Reverting Visual Domain Limitation of Robotic Models Our ReVLA model finetuned at different datasets INSAIT-Institute/ReVLA-Bridge 8B • Updated Feb 17 • 1 • 1 INSAIT-Institute/ReVLA-Fractal Image-to-Text • 8B • Updated Feb 17 • 1
BrokenMath The first benchmark for evaluating LLM sycophancy in mathematical reasoning. INSAIT-Institute/BrokenMath Viewer • Updated Oct 7 • 15.4k • 38 • 1 INSAIT-Institute/BrokenMath-Qwen3-4B 4B • Updated Oct 7 • 44 BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs Paper • 2510.04721 • Published Oct 6
BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs Paper • 2510.04721 • Published Oct 6
Open Proof Corpus A collection of the Open Proof Corpus dataset and the finetuned judging model. INSAIT-Institute/OPC Viewer • Updated Jul 15 • 4.93k • 213 • 12 INSAIT-Institute/OPC-R1-8B 8B • Updated Jun 24 • 4 • 3
BgGPT-Gemma-2 BgGPT-Gemma-2 collection of models. INSAIT-Institute/BgGPT-Gemma-2-27B-IT-v1.0 Text Generation • 27B • Updated Dec 4, 2024 • 34 • 17 INSAIT-Institute/BgGPT-Gemma-2-2.6B-IT-v1.0 Text Generation • 3B • Updated Dec 4, 2024 • 394 • 7 INSAIT-Institute/BgGPT-Gemma-2-9B-IT-v1.0 Text Generation • 9B • Updated Dec 4, 2024 • 65 • 11 INSAIT-Institute/BgGPT-Gemma-2-2.6B-IT-v1.0-GGUF 3B • Updated Nov 19, 2024 • 281 • 4
SPEAR Models of the SPEAR series. INSAIT-Institute/spear1-franka Visual Question Answering • 4B • Updated 26 days ago • 102 • 5
ReVLA: Reverting Visual Domain Limitation of Robotic Models Our ReVLA model finetuned at different datasets INSAIT-Institute/ReVLA-Bridge 8B • Updated Feb 17 • 1 • 1 INSAIT-Institute/ReVLA-Fractal Image-to-Text • 8B • Updated Feb 17 • 1
MamayLM-v1.0-Gemma-3 First Open and Multimodal Ukrainian-focused LLM INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v1.0 Image-Text-to-Text • 12B • Updated Sep 27 • 1.09k • 14 Running 18 18 MamayLM v1.0 Release Blog 🌻 MamayLM v1.0 - now multimodal and even stronger! INSAIT-Institute/MamayLM-Gemma-3-4B-IT-v1.0 Image-Text-to-Text • 4B • Updated Sep 27 • 490 • 9 INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v1.0-GGUF 12B • Updated Sep 9 • 650 • 12
BrokenMath The first benchmark for evaluating LLM sycophancy in mathematical reasoning. INSAIT-Institute/BrokenMath Viewer • Updated Oct 7 • 15.4k • 38 • 1 INSAIT-Institute/BrokenMath-Qwen3-4B 4B • Updated Oct 7 • 44 BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs Paper • 2510.04721 • Published Oct 6
BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs Paper • 2510.04721 • Published Oct 6
MixAT A model collection consisting of different model adapters trained with our adversarial training method MixAT MixAT: Combining Continuous and Discrete Adversarial Training for LLMs Paper • 2505.16947 • Published May 22 INSAIT-Institute/Qwen-32B-MixAT Updated Jun 9 • 11 INSAIT-Institute/Qwen-14B-MixAT Updated Jun 9 • 7 INSAIT-Institute/Qwen-14B-MixAT-GCG Updated Jun 9 • 4
MixAT: Combining Continuous and Discrete Adversarial Training for LLMs Paper • 2505.16947 • Published May 22
Open Proof Corpus A collection of the Open Proof Corpus dataset and the finetuned judging model. INSAIT-Institute/OPC Viewer • Updated Jul 15 • 4.93k • 213 • 12 INSAIT-Institute/OPC-R1-8B 8B • Updated Jun 24 • 4 • 3
MamayLM-Gemma-2 Ukrainian-focused MamayLM model collection, based on Gemma2 INSAIT-Institute/MamayLM-Gemma-2-9B-IT-v0.1 Text Generation • 9B • Updated Jun 17 • 683 • • 25 INSAIT-Institute/MamayLM-Gemma-2-9B-IT-v0.1-GGUF 9B • Updated Apr 22 • 406 • 13
BgGPT-Gemma-2 BgGPT-Gemma-2 collection of models. INSAIT-Institute/BgGPT-Gemma-2-27B-IT-v1.0 Text Generation • 27B • Updated Dec 4, 2024 • 34 • 17 INSAIT-Institute/BgGPT-Gemma-2-2.6B-IT-v1.0 Text Generation • 3B • Updated Dec 4, 2024 • 394 • 7 INSAIT-Institute/BgGPT-Gemma-2-9B-IT-v1.0 Text Generation • 9B • Updated Dec 4, 2024 • 65 • 11 INSAIT-Institute/BgGPT-Gemma-2-2.6B-IT-v1.0-GGUF 3B • Updated Nov 19, 2024 • 281 • 4