Casper

[Casper @CasperWeb3]

@abacaj The problem is that most of the Chinese models are inherently not open and free because they use very restrictive licenses.

[Casper @CasperWeb3]

@ylecun Now we just need to properly open Llama 3. Make it Apache 2.0 or MIT license and you can finally call it truly open source. Follow Mistral, they set a great example.

[Casper @CasperWeb3]

@aton2006 @teknium @markatgradient @togethercompute There is a gap in knowledge in general about how quantized models work. The reason most quantized models are slower is because of the compute overhead of high batch size + dequantization.

[Casper @CasperWeb3]

@WifeyAlpha @ChiefQuant Been trying since summer 2022, maybe one day 🤞

[Casper @CasperWeb3]

This is incredible competition from AMD. They now beat Nvidia in both speed and price for inference. They just need to catch up with robust software - with time, it looks like they will beat Nvidia in the performance/cost trade-off.

https://t.co/0z2wesU6H3

[Casper @CasperWeb3]

@BlancheMinerva Open source is nothing without open and free weights. Last time I checked, all the great Chinese models are gated by custom licenses and applications to even use them.

Doesn’t quite meet my definition of open or free.

[Casper @CasperWeb3]

@far__el Someone uploaded it and split the weights
https://t.co/69f6G5XPlQ

[Casper @CasperWeb3]

@KyeGomezB They forked their own code and improved it, nice. They trained better models too, double nice.

[Casper @CasperWeb3]

@lukebelmar Tether is the last one to go. Until then, crypto is a ticking time bomb.

[Casper @CasperWeb3]

@E0M The authors of this post used GPT-4 to evaluate if a certain phrase was in the text. This does not have any resemblance of a real evaluation and certainly not something I would expect OpenAI to be using

[Casper @CasperWeb3]

@SteveMoraco @OpenAI @GregKamradt These posts are only made to farm reactions on Twitter. Everyone should know that using GPT-4 as an evaluator says nothing about another model as GPT-4 is biased towards itself (surprise)

[Casper @CasperWeb3]

Can someone make GPT-4 good again?

[Casper @CasperWeb3]

@TXMCtrades Good luck with this. There is nothing that gets close to Bloomberg or Refinitiv for real-time data. They collaborate with the government that sends it directly to them.

[Casper @CasperWeb3]

@EMostaque An LLM as good as GPT-4 with MIT license

[Casper @CasperWeb3]

@parth007_96 @woosuk_k They do acknowledge this in the blog from what I’m reading - DS MII is faster in the case of large contexts and small outputs. They also note that they will optimize this part of vLLM with the SplitFuse strategy.

[Casper @CasperWeb3]

@AravSrinivas Unironically, this happened super early with ChatGPT. When security experts who know nothing about search & LLMs start fearmongering about your product - you know that you have made it.

[Casper @CasperWeb3]

That's it, switching from OpenAI to @perplexity_ai. It's simply better in my experience. Now with GPT-4 Turbo, the ChatGPT experienced has dropped for my coding tasks and an effective search for context that Perplexity leverages gives me more accurate answers.

[Bravos Research @bravosresearch]

2008 Financial Crisis timeline 👇

[Casper @CasperWeb3]

@EMostaque Any chance of a commercially compatible license?

[Casper @CasperWeb3]

@osanseviero Where is the code to reproduce these results?