Update README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,9 @@ Long-VITA is a strong long-context visual language model and supports more than
|
|
16 |
|
17 |
- This weight is trained on Ascend NPUs with MindSpeed.
|
18 |
|
19 |
-
-
|
|
|
|
|
20 |
|
21 |
|
22 |
## 📈 Experimental Results
|
@@ -39,6 +41,16 @@ Long-VITA is a strong long-context visual language model and supports more than
|
|
39 |
|
40 |
|
41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
|
43 |
## ACCEPTABLE USE POLICY
|
44 |
|
|
|
16 |
|
17 |
- This weight is trained on Ascend NPUs with MindSpeed.
|
18 |
|
19 |
+
- We also implemented Long-VITA on Megatron with the Transformer Engine to infer and evaluate on Nvidia GPUs. And the converted weight is in https://huggingface.co/VITA-MLLM/Long-VITA-16K_MG.
|
20 |
+
|
21 |
+
- We also implemented Long-VITA on DeepSpeed with the Huggingface Transformers to infer and evaluate on Nvidia GPUs. And the converted weight is in https://huggingface.co/VITA-MLLM/Long-VITA-16K_HF.
|
22 |
|
23 |
|
24 |
## 📈 Experimental Results
|
|
|
41 |
|
42 |
|
43 |
|
44 |
+
## Models
|
45 |
+
|
46 |
+
Model | LLM Size | Training Context | Training Frames | MindSpeed Weights | Megatron Weights | Huggingface Weights
|
47 |
+
---------------:|---------:|-----------------:|----------------:|------------------------------------------------:|---------------------------------------------------:|---------------------------------------------------:
|
48 |
+
Long-VITA-16K | 14B | 16,384 | 64 | https://huggingface.co/VITA-MLLM/Long-VITA-16K | https://huggingface.co/VITA-MLLM/Long-VITA-16K_MG | https://huggingface.co/VITA-MLLM/Long-VITA-16K_HF
|
49 |
+
Long-VITA-128K | 14B | 131,072 | 512 | https://huggingface.co/VITA-MLLM/Long-VITA-128K | https://huggingface.co/VITA-MLLM/Long-VITA-128K_MG | https://huggingface.co/VITA-MLLM/Long-VITA-128K_HF
|
50 |
+
Long-VITA-1M | 14B | 1,048,576 | 4,096 | https://huggingface.co/VITA-MLLM/Long-VITA-1M | https://huggingface.co/VITA-MLLM/Long-VITA-1M_MG | https://huggingface.co/VITA-MLLM/Long-VITA-1M_HF
|
51 |
+
|
52 |
+
|
53 |
+
|
54 |
|
55 |
## ACCEPTABLE USE POLICY
|
56 |
|