Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Document Querying with Qwen2-VL-7B and JSON Output Complete video: I demonstrate how to perform document queries using Qwen2-VL-7B. By simplifying field names, we streamline the prompts, making them more efficient and reusable across different documents. This approach is similar to running SQL queries on a database, but tailored for...

15,981 görüntüleme • 2 yıl önce •via X (Twitter)

6 Yorum

Rubén Aros profil fotoğrafı
Rubén Aros2 yıl önce

It's the best vllm?

Andrej Baranovskij profil fotoğrafı
Andrej Baranovskij2 yıl önce

At the moment yes definitely- qwen2 is the best open source llm with apache license. China rules 🇨🇳👍

optimizium.base.eth (ξ/e) profil fotoğrafı
optimizium.base.eth (ξ/e)2 yıl önce

Still unable to compile flash attention 2 on my Windows machine. :( So annoying.

Andrej Baranovskij profil fotoğrafı
Andrej Baranovskij2 yıl önce

I believe Windows is not well supported platform. Btw, it looks like new Qwen models will be announced next week -

Z❤️H profil fotoğrafı
Z❤️H2 yıl önce

it hallucinante when it should retrieve a correlated informations from multiple lines

Andrej Baranovskij profil fotoğrafı
Andrej Baranovskij2 yıl önce

Not per my tests, qwen2 7b works excellent. For more complex docs use 72b

Benzer Videolar

Molmo by Ai2 - Open source SoTA Multimodal (Vision) Language model, beating Claude 3.5 Sonnet, GPT4V and comparable to GPT4o 🔥 They release four model checkpoints: 1. MolmoE-1B, a mixture of experts model with 1B (active) 7B (total) 2. Molmo-7B-O, most open 7B model 3. Molmo-7B-D, demo model 4. Molmo-72B, best model System Architecture > Input: Multi-scale, multi-crop images generated from the original image. > Vision Encoder: OpenAI's ViT-L/14 336px CLIP model, a powerful ViT, encodes images into vision tokens. > Connector: MLP projects tokens to LLM input space, followed by pooling for dimensionality reduction. > LLM: Decoder-only Transformer, various options (OLMo, OLMoE, Qwen2, Mistral, Gemma2, Phi) with diverse scales and openness. Model Variants > Vision Encoder: Consistent ViT-L/14 CLIP model across variants. > LLM: OLMo-7B-1024, OLMoE-1B-7B-0924, Qwen2 (7B, 72B), Mistral 7B, Gemma2 9B, Phi 3 Medium, offering different capacities and openness levels. Training Strategy > Stage 1: Multimodal pre-training for caption generation with new captioning data. > Stage 2: Supervised fine-tuning on a dataset mixture, updating all parameters. > No RLHF involved, Learning rates adjusted based on component types and pre-training status. > All the weights are available on Hugging Face Hub 🤗 > Compatible with Transformers (Remote Code) Kudos Ai2 for such a brilliant and open work! 🐐 Video credits: Allen AI YT Channel

Vaibhav (VB) Srivastav

80,474 görüntüleme • 2 yıl önce