SB's picture

7 1 6

SB

shb777

·

AI & ML interests

LLM's , Speech 2 Speech and Synthetic Data

Recent Activity

reacted to hexgrad's post with 🔥 about 22 hours ago

https://huggingface.co/hexgrad/Kokoro-82M got an upgrade! ⬆️ More voices, more languages, `pip install kokoro`, and still 82M parameters. GitHub: https://github.com/hexgrad/kokoro PyPI: https://pypi.org/project/kokoro/ Space: https://huggingface.co/spaces/hexgrad/Kokoro-TTS

replied to csabakecskemeti's post 5 days ago

I've run the open llm leaderboard evaluations + hellaswag on https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B and compared to https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct and at first glance R1 do not beat Llama overall. If anyone wants to double check the results are posted here: https://github.com/csabakecskemeti/lm_eval_results Am I made some mistake, or (at least this distilled version) not as good/better than the competition? I'll run the same on the Qwen 7B distilled version too.

updated a dataset 9 days ago

shb777/gemini-flash-2.0-speech

View all activity

Organizations

shb777's activity

upvoted an article 14 days ago

Article

Train 400x faster Static Embedding Models with Sentence Transformers

16 days ago

• 129