243 Photos and videos
1/5
🚀 PilotDeck is now live — the open-source AI agent OS built for all scenarios！
Built by @TsinghuaNLP × ModelBest × @OpenBMB × AI9stars, PilotDeck is here for full memory transparency, intelligent cost routing, and agents that never stop working for you.
🔗 Show Case: pilotdeck.openbmb.cn/pilotde…
💻 GitHub：github.com/OpenBMB/PilotDeck
One person. One fleet of agents. Ship something real. 🔥🧵
71
169
291
284,105
🚀 VoxCPM2 Technical Report is now available on arXiv!
VoxCPM2 is the latest speech generation model in the VoxCPM family. Built with 2B parameters and trained on over 2 million hours of multilingual speech data, it supports 30 languages and 9 Chinese dialects, along with natural-language voice design, controllable voice cloning, and high-fidelity continuation-based voice cloning.
In this technical report, we provide a comprehensive overview of:
🔹 The VoxCPM2 architecture
🔹 A unified sequence formulation for speech generation and control
🔹 The design of AudioVAE for high-fidelity speech reconstruction
🔹 Large-scale multilingual training and evaluation
🔹 Benchmark results across zero-shot and instruction-following TTS tasks
With 16kHz semantic encoding and 48kHz waveform reconstruction, VoxCPM2 delivers high-quality speech generation and achieves SOTA or highly competitive performance on public TTS benchmarks.
To support open research and development, we have open-sourced the model weights, fine-tuning code, and inference toolkit under the Apache 2.0 license.
📄 Paper: arxiv.org/abs/2606.06928
💻 GitHub: github.com/OpenBMB/VoxCPM
We hope VoxCPM2 helps advance the open-source multilingual speech ecosystem. Feedback, experiments, and contributions are always welcome! 🔥
#AI #OpenSource #TTS #SpeechAI #VoiceAI #GenerativeAI #MachineLearning
17
7
70
3,383
🚀 The Build Small Hackathon is officially live! Check it out here:
🔗 build-small-hackathon-field-…
We're proud to partner with @HuggingFace and support builders around the world with OpenBMB models.
Here are some inspiring use cases built with our models:
🪐 MiniCPM-V 4.6 (image / OCR / multimodal)
→ Automated financial document analysis
x.com/OpenBMB/status/2062889…
⚡ MiniCPM5-1B (lightweight, on-device)
→ AI Desktop Pet running entirely on your local device
x.com/OpenBMB/status/2058903…
🌐 MiniCPM-o 4.5 (omni-modal)
→ Real-time video analysis application
x.com/OpenBMB/status/2022341…
🎙️ VoxCPM2 (voice / TTS)
→ Voice cloning application
x.com/OpenBMB/status/2041169…
🏆 $10,000 OpenBMB Special Prize is available for outstanding projects built with our models.
Get creative, try out our models, and see what you can build in this hackathon!
We can't wait to see what you create. ✊
#BuildSmall #MiniCPM #OpenSourceAI #HuggingFace
🚀 VoxCPM 2 is live!
🎉 Another open-source AI #TTS model from China — and one that stands shoulder to shoulder with Qwen3-TTS, while bringing everything into a single unified model. After rapid iterations from V1 (zero-shot cloning) to V1.5 (long-form fine-tuning), #VoxCPM has consistently pushed quality and usability forward.
Now, VoxCPM 2 takes it further:
🔹30 languages — truly global, truly local.
🔹Infinite voice design — type it, hear it, control it. From a whisper to a booming cinematic voice.
🔹Studio-grade audio — 48kHz ultra-high fidelity with emotional depth
🔹Diffusion-Autoregressive cloning — preserves more acoustic and emotional detail than token-based models like Qwen3-TTS
💡 Big shoutout to @grok — used your multi-image video magic for our launch demo. It’s scarily good at keeping visuals consistent across shots. Elon @elonmusk, this one’s for you. 😉
Check the demo & start cloning your dream voice:
🌐 Hugging Face Space: huggingface.co/spaces/openbm…
🤗 Hugging Face Model: huggingface.openbmb.com/mode…
🤖 ModelScope Model: modelscope.cn/models/OpenBMB…
💻 GitHub：github.com/OpenBMB/VoxCPM/
#TTS #AI #VoiceCloning #GrokImagine #ElonMusk #OpenBMB #VoxCPM
6
7
44
7,427
A developer in our community recently built AccountingLLM (quaesto.com/) using MiniCPM-V 4.6 to automate financial document analysis.
You can upload IPO prospectuses, annual reports, or audit filings. It automatically:
📄 Extract financial tables from complex PDFs
🔗 Reconstruct tables split across pages
🔢 Check key figures against accounting equations
⚠️ Flag suspicious entries for human review
The developer already turned this into a commercial service — it's not just a demo, it's an actual product people can use.👇
13
1
32
2,096
💰 Benchmarked against DeepSeek V4 on 169 IPO prospectuses:
MiniCPM-V 4.6 matched on accuracy — financial indicator coverage 96.4% vs 96.8%, error detection identical.
The difference?
▪️ MiniCPM-V 4.6: Open-weights, enabling 100% local deployment.
▪️ DeepSeek V4: API-based, ~¥0.04 per report.
At scale, that gap compounds fast. And with self-hosted deployment, your financial data never leaves your infrastructure.
3
1
6
431
We love seeing developers push MiniCPM-V 4.6 into high-stakes production workflows 🎉
From financial data pipelines and audit tooling to document intelligence and compliance systems — the 1.3B sweet spot keeps showing up.
Built something with MiniCPM-V 4.6? Share your task, prompt, and result below — we'll reshare the best ones 👇
🤗 Hugging Face: huggingface.co/openbmb/MiniC…
💻 GitHub: github.com/OpenBMB/MiniCPM-V
#MiniCPM #OpenBMB #OpenSource #FinancialAI #LLM #Finance
1
5
368
🎉 Exciting News! MiniCPM-o 4.5 has officially been merged into vLLM-Omni! 👏
💡 Currently, it supports simplex non-streaming usage—a solid first step for what's to come.
🚀 The journey continues! We will keep pushing forward with the amazing open-source community to integrate duplex streaming capabilities next.
Get ready for an even more powerful and seamless interactive experience. Stay tuned! 💪
github.com/vllm-project/vllm…
huggingface.co/openbmb/MiniC…
7
6
59
14,715
MiniCPM-V 4.6 is now fully supported in vLLM v0.22.0!
No custom branch. No extra compile.
Just pull the pre-built package and run.
Huge thanks to @vllm_project for the smooth integration! 🤝
🤗 huggingface.co/openbmb/MiniC…
4
1
20
1,464
Just a quick reminder: Build Small Hackathon sign-up closes on June 3!
🏆Total cash prizes: ~$40K
$10K @OpenBMB Special Awards for the best projects using #MiniCPM models.
Don’t miss out! Register now：huggingface.co/build-small-h…
We highly recommend using MiniCPM models — they’re small, powerful, and perfect for this hackathon.
Let’s build something awesome together!🤗🚀
7
11
39
6,960
🏆 Big news! UltraData just hit #1 AND #2 on HuggingFace Trending worldwide! 🎉
Released by OpenBMB × @TsinghuaNLP × Modelbest — two massive open-source datasets now free for everyone:
🔥 Ultra-FineWeb-L3 (web pretraining synthetic data) → 600B tokens (400B English, 200B Chinese) → Largest open-source Chinese pretraining synthetic dataset to date → Built to maximize learnability per token
🔥 UltraData-SFT-2605 (post-training SFT data) → China's first open-source 15M SFT dataset with both thinking & non-thinking annotations → Covers math, code, knowledge & instruction-following → Fully traceable data pipeline
🧱 Both built on the UltraData L0–L4 five-tier data management framework, validated end-to-end on MiniCPM5-1B training.
Free to download now 👇
huggingface.co/datasets/open…
huggingface.co/datasets/open…
#OpenSource #LLM #AI #HuggingFace #MiniCPM #UltraData
6
9
75
29,005
🚀 A 1.3B model handling real work at a mine site and in enterprise offices — faster than your annotation team.
One recent community case shared by developer Jingdong, explored using MiniCPM-V 4.6 for:
✅ore sample counting in lab images
✅vehicle detection and counting from site images
✅mining zone identification from aerial maps
✅Go code completeness checking
Here's what actually happened 🧵
20
12
131
6,075
MiniCPM-V 4.6 is not a magic production replacement. It is useful when the task has clear rules, and clean inputs: counting objects in simple backgrounds, validating document structure, filtering code syntax. It struggles when the task requires spatial reasoning consistency or fine text recognition in complex scenes.
Bottom line: a reliable, low-cost local pre-filter. Not a replacement for human judgment, but a fast first pass that saves time and API spend.
5
9
709
We’re excited to see developers exploring practical multimodal workflows beyond benchmarks🎉
From mine sites and lab counters to enterprise document review and code pipelines — the model is finding its place in production workflows that need speed, low cost, and good-enough accuracy on structured tasks.
Built something with MiniCPM-V 4.6? Drop your task, prompt, and result below — we'll reshare the best ones. 👇
🤗 Hugging Face: huggingface.co/openbmb/MiniC…
💻 GitHub: github.com/OpenBMB/MiniCPM-V
2
9
632