Voxtral Realtime WebGPU
๐ฌ
105
Real-time speech transcription, entirely in your browser.
Tris Warkentin
trisfromgoogle
AI & ML interests
None yet
Recent Activity
liked a Space 4 days ago
mistralai/Voxtral-Realtime-WebGPU liked a Space 11 months ago
nari-labs/Dia-1.6B liked a model 11 months ago
ginipick/Gemma-3-R1984-4BOrganizations
liked a
Space 4 days ago
liked a
Space 11 months ago
liked 2
models 11 months ago
liked a
model about 1 year ago
liked 3
models over 1 year ago
authored a
paper over 1 year ago
posted an update about 2 years ago
Post
1942
Very excited to share the first two official Gemma variants from Google! Today at Google Cloud Next, we announced cutting-edge models for code and research!
First, google/codegemma-release-66152ac7b683e2667abdee11 - a new set of code-focused Gemma models at 2B and 7B, in both pretrained and instruction-tuned variants. These exhibit outstanding performance on academic benchmarks and (in my experience) real-life usage. Read more in the excellent HuggingFace blog: https://huggingface.co/blog/codegemma
Second, ( google/recurrentgemma-release-66152cbdd2d6619cb1665b7a), which is based on the outstanding Google DeepMind research in Griffin: https://arxiv.org/abs/2402.19427. RecurrentGemma is a research variant that enables higher throughput and vastly improved memory usage. We are excited about new architectures, especially in the lightweight Gemma sizes, where innovations like RecurrentGemma can scale modern AI to many more use cases.
For details on the launches of these models, check out our launch blog -- and please do not hesitate to send us feedback. We are excited to see what you build with CodeGemma and RecurrentGemma!
Huge thanks to the Hugging Face team for helping ensure that these models work flawlessly in the Hugging Face ecosystem at launch!
First, google/codegemma-release-66152ac7b683e2667abdee11 - a new set of code-focused Gemma models at 2B and 7B, in both pretrained and instruction-tuned variants. These exhibit outstanding performance on academic benchmarks and (in my experience) real-life usage. Read more in the excellent HuggingFace blog: https://huggingface.co/blog/codegemma
Second, ( google/recurrentgemma-release-66152cbdd2d6619cb1665b7a), which is based on the outstanding Google DeepMind research in Griffin: https://arxiv.org/abs/2402.19427. RecurrentGemma is a research variant that enables higher throughput and vastly improved memory usage. We are excited about new architectures, especially in the lightweight Gemma sizes, where innovations like RecurrentGemma can scale modern AI to many more use cases.
For details on the launches of these models, check out our launch blog -- and please do not hesitate to send us feedback. We are excited to see what you build with CodeGemma and RecurrentGemma!
Huge thanks to the Hugging Face team for helping ensure that these models work flawlessly in the Hugging Face ecosystem at launch!
- 3 replies
reactedto giux78's post with โค๏ธ about 2 years ago
Post
1835
๐ Super @DeepMount00 just released ๐๐ฒ๐บ๐บ๐ฎ_๐ค๐_๐๐ง๐_๐๐ฏ ๐น๐ฒ๐ฎ๐ฑ๐ถ๐ป๐ด the ๐ฅ๐๐ ๐๐ฎ๐๐ธ on the Italian ๐๐๐ _๐๐ง๐_๐๐๐๐๐๐ฅ๐๐ข๐๐ฅ๐. The model is a fine tuned version of Gemma 2B.
Model details: https://huggingface.co/DeepMount00/Gemma_QA_ITA_v3
Explore the full RAG section rankings here: https://huggingface.co/spaces/FinancialSupport/open_ita_llm_leaderboard on section Classifica RAG
Model details: https://huggingface.co/DeepMount00/Gemma_QA_ITA_v3
Explore the full RAG section rankings here: https://huggingface.co/spaces/FinancialSupport/open_ita_llm_leaderboard on section Classifica RAG
authored a
paper about 2 years ago
liked 4
models about 2 years ago
liked a
dataset about 2 years ago
Proposal for Renaming of Gemma-7B Model to Gemma-9B
โค๏ธ๐ 52
4
#34 opened about 2 years ago
by 
ZeroShot-AI
liked a
model about 2 years ago
Is this the same as Gemini Nano?
6
#25 opened about 2 years ago
by 
nonetrix