AI๊ฐ ์์ง์ด๊ณ ๋ฏธ๋๊ฐ ์
๋ฐ์ดํธ๋ฉ๋๋ค.InternVL-Chat-V1-2
We are excited to introduce ๐ค InternVL-Chat-V1-2. Inspired by LLaVA-NeXT-34B, we have also adopted Nous-Hermes-2-Yi-34B as the language model. Below is the pipeline. From the experimental results, we've observed that **a stronger language model (34B) can better leverage the powerful capabilities of our vision foundation model.** For better training reproducibility, we follow the minimalist design and data efficiency similar to LLaVA-NeXT. To reduce training costs, we provide a pre-trained MLP projector and only employ around 1.2 million visual instruction tuning samples for SFT. Our model has a total of 40 billion parameters and can be trained within 1.5 days using 32 A100 GPUs. The code, data, and model have been made publicly available.
๋ฒ์ญ ์ค๋น ์ค์ ๋๋ค. ์๋ฌธ์ ํ์ํฉ๋๋ค.
We are excited to introduce ๐ค InternVL-Chat-V1-2. Inspired by LLaVA-NeXT-34B, we have also adopted Nous-Hermes-2-Yi-34B as the language model. Below is the pipeline. From the experimental results, we've observed that **a stronger language model (34B) can better leverage the powerful capabilities of our vision foundation model.** For better training reproducibility, we follow the minimalist design and data efficiency similar to LLaVA-NeXT. To reduce training costs, we provide a pre-trained MLP projector and only employ around 1.2 million visual instruction tuning samples for SFT. Our model has a total of 40 billion parameters and can be trained within 1.5 days using 32 A100 GPUs. The code, data, and model have been made publicly available.