Repository Issue Activity (beta)

#1131 MiniCPM-o 4.5: greedy decoding degenerates (empty / repetition-loop outputs) on long multimodal prefixes (>12k tokens)

#1130 Duplicate — closed

#1129 Discord invite invalid

#1127 [vllm-omni] - Does MiniCPM-o 4.5 officially support TTS generation beyond 4,096 Talker positions?

#1093 MiniCPM-o 4.5 技术报告细节疑问。

#1095 MiniCPM V4.6是否可以直接替换text_config组成新的模型？

#1101 💡 [REQUEST] - Multiuse benchmarks

#1123 [BUG] Free API key is invalid

#1126 Verify evals on Papers with Code

#1121 [BUG] <title>按照MiniCPM-V 4.6 vLLM 部署指南部署时，加载权重出现报错

#1124 [BUG] <title>minicpm-o 4.5的实时API概述链接无法打开

#1122 [MiniCPM-o 4.5] Eval config behind WorldSense 55.7 (slicing / frames / audio / thinking), and use_image_id=True degenerating on long frame sequences

#1120 MiniCPM-o 4.5 video-only LoRA on Hugging Face Jobs: compatibility notes and workarounds

#1118 [MiniCPM-o 4.5] LayerDrop appears disabled during training because 'encoder_layerdrop' is set to '0.0'

#1115 Reproduction gap for MiniCPM-V-4.6 on AI2D_TEST and MMMU_DEV_VAL with VLMEvalKit

#1116 [BUG] <title>MiniCPM-o 4.5模型上下文达到1.1w，模型agent能力严重退化

#1114 eval_mm directory not updated for MiniCPM-V 4.6

#1113 vllm部署报错 AttributeError: 'MiniCPMV4_6ImageProcessor' object has no attribute 'version'

#1110 MiniCPM-o 4.5 全双工模式是否支持 RAG？

#1109 MiniCPM-V 4.6 as a VLM backbone in StarVLA for LIBERO robot manipulation

#1112 💡 [REQUEST] - MiniCPM-o 微信群二维码过期了

#1111 💡 Support thinking in audio input

#1084 How to finetune audio duplex ability?

#1106 MiniCPM-V-4.6-Instruct 这个模型，哪里可以下载

#1105 MiniCPM V4.6 本地部署，到底使用什么工具来部署效果最好？