Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Orca 2: Teaching Small Language Models How to Reason

arxiv.org

Post reply on HN
Print view View original

31–40 of 82 posts

Re: Orca 2: Teaching Small Language Models How to Reason

#31

Post by FFP999 »

intended wrote: post #29
coderaptor wrote: post #25

Earlier quoted context omitted.

I haven’t heard a definition of “reasoning” or “thinking” that proves humans aren’t doing exactly that same probabilistic regurgitation. I don’t think it’s possible to prove; feels like a philosophical question.

It’s possible to prove. Use an LLM to do a real world task that you should be able to achieve by reasoning.

> Use an LLM to do a real world task that you should be able to achieve by reasoning.

Such as explaining the logical fallacies in this argument and the one above?

Re: Orca 2: Teaching Small Language Models How to Reason

#32

Post by schleck8 »

alecco wrote: post #16

> Progressive Learning: We start with LLaMA-2-7B or LLaMA-2-13B checkpoint and finetune it on the train split of FLAN-v2 dataset for one epoch. Note that FLAN-v2 dataset contains both zero-shot and few-shot problems. We then train on 5 million ChatGPT data from Orca 1 for 3 epochs. Then we train on the combination of 1 million GPT-4 data from Orca 1 and Orca 2’s 817K data for 4 epochs. I think people are missing why…

Yeah, the 13b model outperforms the 70b Llama 2. Goes to show how much potential there is on the software optimization front as opposed to just scaling in size

Re: Orca 2: Teaching Small Language Models How to Reason

#33

Post by schleck8 »

FFP999 wrote: post #21
intended wrote: post #8

I really really want this to work. However at this point - benchmark success is about as effective as results from someone who has been “taught the test” If say… Merck wanted to use this same model to reason out a logistics issue, or apply it to some business problem at scale - you’d have to deal with hallucinations all over the place. The best analogy I have right now is that improved results on benchmarks are like…

At the moment I read "how to reason" in the headline my bullshit detector started to go off. LLMs do not reason, they do not think, they are not AGI. They generate by regurgitating.

AGI doesn't reason either. Noone defines AGI as "AI, but with reasoning". It's "AI, that outperforms humans at all disciplines, by any degree" usually. Maybe you confused it with ASI, but even then reasoning isn't a requirement afaik.

Re: Orca 2: Teaching Small Language Models How to Reason

#34

Post by schleck8 »

GaggiX wrote: post #7
davidkunz wrote: post #4

For smaller models, I'm impressed by Mistral-7b or fine-tuned variants like Zephyr. I use it regularly in Neovim[1] for mundane tasks (grammar correction, summaries, ...). I'm curious how Orca 2 performs, downloading it right now. [1]: with https://github.com/David-Kunz/gen.nvim

Also OpenChat-3.5v model (It has 7B parameters, I think it is also a Mistral finetuning), demo: https://openchat.team/

Nice, it passes the weather test. I always ask open source models what the weather is like and see wether it hallucinates my location and a forecast. A few months ago without exception all models I tried (even larger ones) would just make up a temperature. Now it replies as it should Cool!

> what's the weather like today?

> I'm sorry, but I can't provide real-time weather information. However, I can help you with general information about weather conditions and forecasting.

Re: Orca 2: Teaching Small Language Models How to Reason

#35

Post by T-A »

alecco wrote: post #16

> Progressive Learning: We start with LLaMA-2-7B or LLaMA-2-13B checkpoint and finetune it on the train split of FLAN-v2 dataset for one epoch. Note that FLAN-v2 dataset contains both zero-shot and few-shot problems. We then train on 5 million ChatGPT data from Orca 1 for 3 epochs. Then we train on the combination of 1 million GPT-4 data from Orca 1 and Orca 2’s 817K data for 4 epochs. I think people are missing why…

...and quantized ones from the usual suspect:

https://huggingface.co/TheBloke/Orca-2-7B-GGUF

https://huggingface.co/TheBloke/Orca-2-13B-GGUF

The 7B Q5_K_M one is small enough to run on an 8GB consumer GPU.

Re: Orca 2: Teaching Small Language Models How to Reason

#36

Post by CAP_NET_ADMIN »

coderaptor wrote: post #25
FFP999 wrote: post #21

Earlier quoted context omitted.

At the moment I read "how to reason" in the headline my bullshit detector started to go off. LLMs do not reason, they do not think, they are not AGI. They generate by regurgitating.

I haven’t heard a definition of “reasoning” or “thinking” that proves humans aren’t doing exactly that same probabilistic regurgitation. I don’t think it’s possible to prove; feels like a philosophical question.

LLMs can be trained on all the math books in the world, starting from the easiest to the most advanced, they can regurgitate them almost perfectly, yet they won't apply the concepts in those books to their actions. I'd count the ability to learn new concepts and methods, then being able to use them as "reasoning".

Re: Orca 2: Teaching Small Language Models How to Reason

#37

Post by pelorat »

FFP999 wrote: post #21
intended wrote: post #8

I really really want this to work. However at this point - benchmark success is about as effective as results from someone who has been “taught the test” If say… Merck wanted to use this same model to reason out a logistics issue, or apply it to some business problem at scale - you’d have to deal with hallucinations all over the place. The best analogy I have right now is that improved results on benchmarks are like…

At the moment I read "how to reason" in the headline my bullshit detector started to go off. LLMs do not reason, they do not think, they are not AGI. They generate by regurgitating.

Reasoning is a learnt concept that involves retrieving memories and running them though an algorithm, also retrieved from memory, and then you loop the process until a classifier deems the result to be adequate to the given goal.

Re: Orca 2: Teaching Small Language Models How to Reason

#38

Post by motoxpro »

FFP999 wrote: post #31
intended wrote: post #29

Earlier quoted context omitted.

It’s possible to prove. Use an LLM to do a real world task that you should be able to achieve by reasoning.

> Use an LLM to do a real world task that you should be able to achieve by reasoning. Such as explaining the logical fallacies in this argument and the one above?

I mean I know you're joking but yes, it would be able to do that.

Re: Orca 2: Teaching Small Language Models How to Reason

#39

Post by margorczynski »

CAP_NET_ADMIN wrote: post #36
coderaptor wrote: post #25

Earlier quoted context omitted.

I haven’t heard a definition of “reasoning” or “thinking” that proves humans aren’t doing exactly that same probabilistic regurgitation. I don’t think it’s possible to prove; feels like a philosophical question.

LLMs can be trained on all the math books in the world, starting from the easiest to the most advanced, they can regurgitate them almost perfectly, yet they won't apply the concepts in those books to their actions. I'd count the ability to learn new concepts and methods, then being able to use them as "reasoning".

Aren't there quite a few examples of LLMs giving out-of-distribution answers to stated problems? I think there are two issues with LLMs and reasoning:

1. They are single-pass and static - you "fake" short-term memory by re-feeding the questions with it answer 2. They have no real goal to achieve - one that it would split into sub-goals, plan to achieve them, estimate the returns of each, etc.

As for 2. I think this is the main point of e.g. LeCun in that LLMs in themselvs are simply single-modality world models and they lack other components to make them true agents capable of reasoning.

Post reply on HN