Hugging Face's logo

OpenGVLab
/
InternVideo2_5_Chat_8B

Video-Text-to-Text
Transformers
Safetensors
English
internvl_chat
feature-extraction
multimodal
custom_code
Eval Results (legacy)
Model card Files
xet
 Community
16
ynhe commited on
Commit
87680fe
·
verified ·
1 Parent(s): 2d2f9c8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -100,7 +100,7 @@ We measured the average inference speed (tokens/s) of generating 1024 new tokens
100
  |Quantization | Speed (3022 tokens) | Speed (8192 tokens) w/o encoder| Speed(8192 tokens) w/ encoder|
101
  |--- |--- |---| ---|
102
  |BF16 | 33.40 | 31.91 | 21.33|
103
- |INT4 | - | 31.95 | - |
104
 
105
  The profiling runs on a single A800-SXM4-80G GPU with PyTorch 2.4.0 and CUDA 12.1.
106
 
 
100
  |Quantization | Speed (3022 tokens) | Speed (8192 tokens) w/o encoder| Speed(8192 tokens) w/ encoder|
101
  |--- |--- |---| ---|
102
  |BF16 | 33.40 | 31.91 | 21.33|
103
+ |INT4 | - | 31.95 | 26.37|
104
 
105
  The profiling runs on a single A800-SXM4-80G GPU with PyTorch 2.4.0 and CUDA 12.1.
106