Hugging Face's logo
Ngodi's picture
2 4

Ngodi

mrngodi
·

AI & ML interests

RNN, CNN, LLM, LVM,

Recent Activity

replied to JustinLin610's post about 1 month ago
Finally, Qwen1.5-110B is out! With weights and demo! Blog: https://qwenlm.github.io/blog/qwen1.5-110b/ Demo: https://huggingface.co./spaces/Qwen/Qwen1.5-110B-Chat-demo Base: https://huggingface.co./Qwen/Qwen1.5-110B Chat: https://huggingface.co./Qwen/Qwen1.5-110B-Chat This model has some specific features: * GQA * 32K token context length * Multilingual support We feel good about its performance on benchmarks, including those for base models and chat models, but we still need more of your testing and feedback to help us know its capabilities and limitations! Additionally, the base model has not learned chatml tokens. Yeah if you use chatml format, you need to be careful about it! Enjoy and stay tuned for Qwen2!
reacted to merve's post with 👍 about 1 month ago
A complete RAG pipeline includes a reranker, which ranks the documents to find the best document 📓 Same goes for multimodal RAG, multimodal rerankers which we can integrate to multimodal RAG pipelines! Learn how to build a complete multimodal RAG pipeline with https://huggingface.co./vidore/colqwen2-v1.0 as retriever, https://huggingface.co./lightonai/MonoQwen2-VL-v0.1 as reranker, https://huggingface.co./Qwen/Qwen2-VL-7B-Instruct as VLM in this notebook that runs on a GPU as small as L4 🔥 https://huggingface.co./learn/cookbook/multimodal_rag_using_document_retrieval_and_reranker_and_vlms
reacted to merve's post with 🧠 about 1 month ago
A complete RAG pipeline includes a reranker, which ranks the documents to find the best document 📓 Same goes for multimodal RAG, multimodal rerankers which we can integrate to multimodal RAG pipelines! Learn how to build a complete multimodal RAG pipeline with https://huggingface.co./vidore/colqwen2-v1.0 as retriever, https://huggingface.co./lightonai/MonoQwen2-VL-v0.1 as reranker, https://huggingface.co./Qwen/Qwen2-VL-7B-Instruct as VLM in this notebook that runs on a GPU as small as L4 🔥 https://huggingface.co./learn/cookbook/multimodal_rag_using_document_retrieval_and_reranker_and_vlms
View all activity

Organizations

None yet

mrngodi's activity

replied to JustinLin610's post about 1 month ago
view reply

Nice job!

I gave it this image and asked it to be short and clear and summarize what's on the image. Did well in chinese!

in-chinese.png

But the same request in English - I got a looong response! Three Final Answers!!... I suppose it's a Chinese first model?

long-article.png
reacted to merve's post with 👍🧠 about 1 month ago
view post
Post
1792
A complete RAG pipeline includes a reranker, which ranks the documents to find the best document 📓
Same goes for multimodal RAG, multimodal rerankers which we can integrate to multimodal RAG pipelines!
Learn how to build a complete multimodal RAG pipeline with vidore/colqwen2-v1.0 as retriever, lightonai/MonoQwen2-VL-v0.1 as reranker, Qwen/Qwen2-VL-7B-Instruct as VLM in this notebook that runs on a GPU as small as L4 🔥 https://huggingface.co./learn/cookbook/multimodal_rag_using_document_retrieval_and_reranker_and_vlms
  • 1 reply
·
liked a model 3 months ago
updated 3 models 3 months ago
liked a dataset 3 months ago
upvoted a collection 3 months ago
liked a dataset 3 months ago
liked a model 4 months ago
upvoted an article 6 months ago
view article
Article

Welcome FalconMamba: The first strong attention-free 7B model

• 108