glenn2 commited on
Commit
80c9ef5
·
verified ·
1 Parent(s): 2904bfe

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ LFG-3 is an audio-language model that fuses the best-in-class conversational int
17
 
18
  The model is the third iteration in a personal learning journey to answer the question: "Can I stand on the shoulders of giants and use limited compute resources to build a standout model that can understand what and how you say things, not just speech to text?"
19
 
20
- The answer is Yes. LFG-3 ranks #1 on Voice Bench at the time of this release.
21
 
22
 
23
  LFG-3 serves as an open exploration of just how adaptable the Gemma architecture can be for independent developers building multimodal applications.
 
17
 
18
  The model is the third iteration in a personal learning journey to answer the question: "Can I stand on the shoulders of giants and use limited compute resources to build a standout model that can understand what and how you say things, not just speech to text?"
19
 
20
+ The answer is Yes. LFG-3 was trained entirely on a single H100 from my house on nights and weekends. It ranks #1 on Voice Bench at the time of this release.
21
 
22
 
23
  LFG-3 serves as an open exploration of just how adaptable the Gemma architecture can be for independent developers building multimodal applications.