Image-Text-to-Text
Transformers
Safetensors
Cosmos
English
qwen2_5_vl
image-to-text
nvidia
conversational
text-generation-inference
harrim-nv commited on
Commit
375e240
·
verified ·
1 Parent(s): 3210bec

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -7
README.md CHANGED
@@ -93,13 +93,6 @@ Cosmos-Reason1-7B:<br>
93
  * Other components (output projection layer): 545.00M (544,997,376)
94
 
95
 
96
- ## Computational Load:
97
-
98
- * Cumulative Compute: 3.2603016e+21 FLOPS
99
- * Estimated Energy and Emissions for Model Training:
100
- * Total kWh = 16658432
101
- * Total Emissions (tCO2e) = 5380.674
102
-
103
  ## Input
104
 
105
  **Input Type(s)**: Text+Video/Image
 
93
  * Other components (output projection layer): 545.00M (544,997,376)
94
 
95
 
 
 
 
 
 
 
 
96
  ## Input
97
 
98
  **Input Type(s)**: Text+Video/Image