Tencent released the weights for the Hy4 model, allowing commercial use and modification. However, model-service operators that meet certain criteria must obtain separate permission. The default deployment in vLLM uses eight B300 GPUs.
Source: Read the original article
Disclaimer: this content is for information purposes only and is not financial advice. Cryptocurrencies are highly volatile: you may lose all of your capital. Always do your own research. Legal notice


