Tencent Hunyuan's open embodied vision-language foundation model for physical-world agents, with roughly 30B total and 3B active parameters, released with weights and Transformers/vLLM inference code.
881Tencent Hunyuan's open embodied vision-language foundation model for physical-world agents, with roughly 30B total and 3B active parameters, released with weights and Transformers/vLLM inference code.