LLMS

→ View original post on X — @craigbrownphd

Claude vs Gemini: Choosing the Right Language Model

By

@craigbrownphd

–

29 September 2024 17h50

Claude vs Gemini: A Guide to Choose the Right Model: Introduction Within the quickly changing field of artificial intelligence, two language models, Claude and Gemini,… https://
analyticsvidhya.com/blog/2024/09/c
laude-vs-gemini/?utm_source=dlvr.it&utm_medium=twitter
… #DataAnalytics #DataScience #DataDriven #CIO #BigData #AI #CTO #ArtificialIntelligence

Model Merging Techniques and Hidden Representation Dynamics

By

–

29 September 2024 17h03

I'd say it barely works tbh… 🙂 It really depends on the type of merge and whether you retrain it or not. In this case, it's not really "working". The additional layers seem to push the hidden representations into new areas, which may or may not be interesting, depending on

Distillation vs DPO: Model Optimization Techniques Comparison

By

–

29 September 2024 16h55

Yes, for sure. Distillation would be ideal but DPO would also work.

Model Merges and 34B Evaluation Updates

By

–

29 September 2024 15h27

I would usually assume that but my merges do work though. It might have been fixed after the 34B eval?

→ View original post on X — @thom_wolf

Open Multimodal LLM Releases Close Gap with Closed-Source Models

By

@thom_wolf

–

29 September 2024 14h45

Celebrating a crazy month of "Open Multimodal LLM Releases"! If you haven't followed it several research labs have release impressively capable open multimodal LLMs in September 2024: Qwen-VL, Pixtral, LLama 3.2 and Molmo, seriously closing the gap with closed-source model

Self-Merge Experiments: 52B Model Success in BBH and MATH

By

–

29 September 2024 12h59

I want to share some results related to my self-merge experiments: – The 47B merge doesn't work: replicating blocks > layers (apologies for doubting it) – The 52B is successful in BBH and MATH Lvl 5. However, there might be an issue with the original model's MATH eval. This is

→ View original post on X — @testingcatalog

Observations on OpenAI Prototype UI Changes

By

@testingcatalog

–

29 September 2024 8h47

Yes, this was in the earlier prototype. Now it is not there anymore on MacOS at least. I had more UI examples over here https://
testingcatalog.com/openai-will-in
troduce-her-on-may-13-here-is-what-she-looks-like/
…