Update README.md
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ Github: https://github.com/VITA-MLLM/Long-VITA
|
|
15 |
|
16 |
Long-VITA is a strong long-context visual language model and supports more than 1 million tokens.
|
17 |
|
18 |
-
- Long-VITA-16K weights are trained on Ascend NPUs with MindSpeed.
|
19 |
|
20 |
- We also implemented Long-VITA on Megatron with the Transformer Engine to infer and evaluate on Nvidia GPUs. The converted weight is at https://huggingface.co/VITA-MLLM/Long-VITA-16K_MG.
|
21 |
|
|
|
15 |
|
16 |
Long-VITA is a strong long-context visual language model and supports more than 1 million tokens.
|
17 |
|
18 |
+
- Long-VITA-16K weights are trained on Ascend NPUs with MindSpeed. The original weight is at https://huggingface.co/VITA-MLLM/Long-VITA-16K.
|
19 |
|
20 |
- We also implemented Long-VITA on Megatron with the Transformer Engine to infer and evaluate on Nvidia GPUs. The converted weight is at https://huggingface.co/VITA-MLLM/Long-VITA-16K_MG.
|
21 |
|