Sources
Loading...
Additional media
Loading...
DeepNewz, mobile.
People-sourced. AI-powered. Unbiased News.
Hyperbolic Labs has announced the hosting of several advanced Vision Language Models (VLMs), including Pixtral-12B from MistralAI and Qwen2-VL-7B from Alibaba Qwen. These models are being served in BF16 and are particularly effective in handwriting recognition and OCR tasks, with Qwen2-VL-7B achieving 100% accuracy in tests. Qwen2-VL-7B also ranks 8th on the leaderboard for models under 10 billion parameters, making it the best open-source VLM in its category. Additionally, Qwen2-VL-Max-0809 (72B) outperforms GPT-4o-0806 and ranks 1st overall. Hyperbolic Labs has also retired Reflection 70B in favor of DeepSeek-V2.5, which combines DeepSeek-v2 and DeepSeek-v2-Coder, and is running on 8xH100 GPUs. The models are currently available for free through Hyperbolic Labs' API and playground. Qwen2-VL 70B has shown notable performance on DocVQA, OCRBench, and InfoQA.
We @hyperbolic_labs now hosting VLMs (Vision Language Models): Qwen2-VL-7B-Instruct from @Alibaba_Qwen and Pixtral-12B from @MistralAI are served in BF16 🔥 I compared them in our playground head-to-head with 2 tests: 1. Handwriting recognition/OCR: Qwen2-VL-7B: 100% accuracy;… https://t.co/mj2m3SAxkb
We @hyperbolic_labs are now hosting Vision Language Models: Pixtral-12B from @MistralAI and Qwen2-VL-7B-Instruct from @Alibaba_Qwen! 🔥 > Use our API or playground to play w/ it > good at handwriting recognition/OCR. In my test below, Qwen2-VL-7B gets 100% accuracy (wow), while… https://t.co/76etAJvX9p
We @hyperbolic_labs now hosting Vision language models! 👁️ * Pixtral-12B from @MistralAI and Qwen2-VL-7B from @Alibaba_Qwen are both live! > both served in BF16 > they're really good at handwriting recognition/OCR (even decipher doctors' bad handwriting?) > free for now (we… https://t.co/3uRbxsMbMq
