patricklifixie commited on
Commit
adbc420
·
verified ·
1 Parent(s): 09b0e5d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -6
README.md CHANGED
@@ -125,12 +125,6 @@ Supervised speech instruction finetuning via knowledge-distillation. For more in
125
  - **Training regime:** BF16 mixed precision training
126
  - **Hardward used:** 8x H100 GPUs
127
 
128
- #### Speeds, Sizes, Times
129
-
130
- The current version of Ultravox, when invoked with audio content, has a time-to-first-token (TTFT) of approximately 150ms, and a tokens-per-second rate of ~50-100 when using an A100-40GB GPU, all using a Llama 3.3 70B backbone.
131
-
132
- Check out the audio tab on [TheFastest.ai](https://thefastest.ai/?m=audio) for daily benchmarks and a comparison with other existing models.
133
-
134
  ## Evaluation
135
 
136
  | | Ultravox 0.4 70B | Ultravox 0.4.1 70B | **Ultravox 0.5 70B** |
 
125
  - **Training regime:** BF16 mixed precision training
126
  - **Hardward used:** 8x H100 GPUs
127
 
 
 
 
 
 
 
128
  ## Evaluation
129
 
130
  | | Ultravox 0.4 70B | Ultravox 0.4.1 70B | **Ultravox 0.5 70B** |