BosonAI (@boson

BosonAI

56 posts

BosonAI

@boson_ai

Intelligent agents as human companions and helpers

Santa Clara

Joined February 2023

Following

1,004

Followers

BosonAI
@boson_ai
Jun 6, 2024
Excited to release Higgs-Llama-3-70B, the first model in our Higgs family of LLM for role playing - Post-trained from Llama-3-base - Excluded benchmark data (including training examples) from our fine-tuning data - Blog: boson.ai/higgs-opensour… - 🤗: huggingface.co/bosonai/Higgs-…
16K
BosonAI
@boson_ai
Jun 6, 2024
Congrats to the Qwen2 release👏 We tuned Qwen1 models for our customers last year, they were very happy!😄 Higgs-Llama-3-70B and Qwen2-70B-Instruct reported very comparable results😆😆😆 Results by joining benchmark tables with Llama-3-70B-Instruct as the key
4.8K
BosonAI
@boson_ai
Jul 18, 2024
Excited to share Higgs-V2, improved both general and roleplaying abilities. The performance boost comes from the in-house built reward model. More at boson.ai/higgs-v2/
6.4K
BosonAI
@boson_ai
Jul 22, 2025
1/3 We are excited to announce our opensource release of #BosonAI #HiggsAudio v2 (boson.ai/blog/higgs-aud…), a SToA multimodal LLM for audio generation. #HiggsAudio v2 is the first OSS large audio model excels at multi-speakers cloning, emotionally competent voice generation.
Boson AI
From boson.ai
974
BosonAI
@boson_ai
Jul 22, 2025
Multi-speaker conversations can be tricky for AI models. #HiggsAudio makes it easy. #HiggsAudio v2 supports end2end voice clone and generation, see live #HiggsAudio translating and cloning simultaneously youtu.be/br9zBkpcaco. #HiggsAudio inference can run on a Jetson Orin Nano
1.9K
BosonAI
@boson_ai
Jul 22, 2025
2/3 #HiggsAudiov2 is trained on a massive corpus of over 10M hours of high-quality audio data, annotated using BosonAI’s #ASR, and #LLM models. on #Github: github.com/boson-ai/higgs… + on #HuggingFace huggingface.co/bosonai/higgs-…).
GitHub - boson-ai/higgs-audio: Text-audio foundation model from Boson AI
From github.com
716
BosonAI
@boson_ai
Jul 22, 2025
3/3 HiggsAudiov2 adopts Dual-FFN architecture that is capable of handling text and audio tokens jointly. Higgs Audio v2 has achieved state-of-art performance, beats “gpt‑4o‑mini‑tts” with 75.7% win rate on “Emotions” and 55.7 % on “Questions” in EmergentTTS‑Eval.
794
BosonAI
@boson_ai
Aug 23, 2025
youtu.be/VGFP_xjWLoE Higgs-audio whipped up something relaxing —a fully AI-generated track with lyrics, beat, and chorus all in one, zero-shot.
849