Generalist embedding models are better at short-context clinical semantic search than specialized embedding models
https://huggingface.co/papers/2401.01943

GPT-4V(ision) is a Generalist Web Agent, if Grounded
https://huggingface.co/papers/2401.01614

اینم مدل ترین شده این در هاگینگ فیس


https://huggingface.co/spaces/mostafaamiri/persianllama

#مقاله #ایده_جذاب

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

500 AI Machine learning Deep learning Computer vision NLP Projects with code

https://github.com/ashishpatel26/500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code

چند مورد از TTS models اوپن سورس شده:

▪️ XTTS
▪️ YourTTS
▪️ FastSpeech2
▪️ VITS
▪️ TorToiSe
▪️ Pheme
▪️ EmotiVoice
▪️ StyleTTS
▪️ pflowtts_pytorch
▪️ VALL-E
▪️ OpenVoice
▪️ piper

پ.ن: موردهای یگه میشناسید کامنت کنید

#مقاله #ایده_جذاب

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

مقاله جالبیه این
▪️ NASA and IBM Openly Release Geospatial AI Foundation Model for NASA Earth Observation Data


#مقاله #ایده_جذاب

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

اگر میخواید از بعضی مقاله های پولی مثل مدیوم استفاده کنید.
حتما یه سری به لینک های زیر بزنید.

📌 https://1ft.io

📌 https://12ft.io

📌 https://github.com/iamadamdev/bypass-paywalls-chrome

#مقاله

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

یه دوره جدید از امازون
▪️ Generative AI Foundations on AWS Technical Deep Dive Series

#منابع #هوش_مصنوعی #

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

هرچی خوندین تا حالا بزارین کنار اینو بخونین
https://avt.im/blog/on-successful-research/


#مقاله

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

The main idea is to take two small models:
- a small base model (M2)
- a finetuned base model (M3)
1) The goal was to
A. instruction-tuning
B. domain adaptation
C. task-specific finetuning

improve a Llama 2 70B Base model to the level of Llama 2 70B Chat but without doing any RLHF to get the model from Base -> Chat.

2) They took a 10x smaller Llama 2 7B model and instruction-finetuned it.

3) After finetuning, they computed the difference in logits over the output vocabulary between 7B Base and 7B Finetuned

4) They applied the difference from 3) to the Llama 2 70B Base model. This pushed the 70B Base model's performance pretty close to 70B Chat.

▪️ Tuning Language Models by Proxy

#مقاله #ایده_جذاب

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

تاریخچه Text Embeddings

▪️ The 1950-2024 Text Embeddings Evolution Poster

#مقاله #ایده_جذاب

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

Faster RAG re-ranking with ColBERT

After re-ranking using GPT-4 yesterday, I tested out ColBERT for re-ranking today.

Test:
• Re-ranking Airbnb's 10-K, like before.

Results:
• ColBERT and GPT-4 were identical in ranking quality

However, ColBERT was lightning-fast.

Re-ranking speed:
• 3.41 secs for ColBERT
• 25.47 secs for GPT-4

ColBERT is a game-changer for re-ranking tasks.

Excited to try it out in production with Oxygen.

https://gist.github.com/virattt/b140fb4bf549b6125d53aa153dc53be6

Overcome Lost In Middle Phenomenon In RAG Using LongContextRetriver

▪️Lost in the Middle: How Language Models Use Long Contexts
https://arxiv.org/pdf/2307.03172.pdf

یه دوره کلاسی رایگان #علم_داده از دانشگاه نیویورک

▪️ Data Science for Everyone: course text
▪️ NYU course: Data Science for Everyone

#منابع #مقدماتی #کلاس_آموزشی

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person

کورس کلاسی جدید از دانشگاه CMU

▪️ Neural code generation / Spring 2024
▪️ Foundations: Pretraining and scaling laws

#منابع #مقدماتی #کلاس_آموزشی

🔸 مطالب بیشتر 👇👇

✅ @AI_DeepMind
🔸 @AI_Person