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

Alpaca: A strong open-source instruction-following model

crfm.stanford.edu

Post reply on HN
Print view View original

91–100 of 313 posts

Re: Alpaca: A strong open-source instruction-following model

#91

Post by z3t4 »

londons_explore wrote: post #23

The training data doesn't seem to be great quality... "instruction": "Calculate the sum of each column in the following table.", "input": "2 | 3 | 4\n 5 | 6 | 7", "output": "2+3+4 = 9\n5+6+7 = 18" I think better results could be obtained by manually going through these 52,000 training examples - even a couple of seconds per example should be enough to weed out obviously wrong ones, and should only take <$1000 of huma…

Training a model to do math is impossible. If you tell a child that 1+1=2 10+10=20 100+100=200 an "AI" can not figure out that 1000+1000=2000 like a child can.

Re: Alpaca: A strong open-source instruction-following model

#92

Post by azeirah »

bogwog wrote: post #31
adam_arthur wrote: post #8

Pretty exciting to see the democratization of this tech. The next wave of innovation seems like it’ll be much less centralized into a handful of big companies. Even more powerful closed door LLMs will appear, but already so much utility out of these that can run on consumer hardware.

Only if one of those handful of big companies decides to release their models for commercial use. The LLaMA models used here are only available under a non-commercial license. Can’t build anything significant with leaked models. Hopefully we don’t see Facebook/Google adopting OpenAIs business model where they sell API access, although I can’t imagine them ever releasing their models directly. The last thing they woul…

Is there a reason why we aren't using BLOOM's model?

It's huge, 160B parameters. It's open, it's free, it's been out there for a while.

Is something wrong with it? Using outdated training data? Using outdated training techniques? Or is it just not well known enough -- ie, not in the news at the right time.

Re: Alpaca: A strong open-source instruction-following model

#93

Post by wkat4242 »

oceanplexian wrote: post #58
bogwog wrote: post #31

Earlier quoted context omitted.

Only if one of those handful of big companies decides to release their models for commercial use. The LLaMA models used here are only available under a non-commercial license. Can’t build anything significant with leaked models. Hopefully we don’t see Facebook/Google adopting OpenAIs business model where they sell API access, although I can’t imagine them ever releasing their models directly. The last thing they woul…

I think anyone can train one of these models. “anyone” being someone who can throw $1-5M in cloud resources at compute. Or a bored sysadmin with access to a few thousand GPUs and a cool boss. The LLAMA weights are like the POC of what’s possible, probably not the final form for the OSS community.

Sounds like a great Kickstarter option for a truly free model. I'd back it.

Re: Alpaca: A strong open-source instruction-following model

#94

Post by ethanbond »

nlowell wrote: post #80
beepbooptheory wrote: post #52

Earlier quoted context omitted.

Its really just because of boring old liability, nothing more. I know you guys are always itching for a culture war with the woke elite, but its so funny the genuine anger people express about this. Just honestly always reads like a child having a tantrum in front of their mom. Can't yall like pick on the opinions of teenagers like you normally do? This very project shows you can make your own AI as edgy as you want…

You're missing the point and willfully characterizing others as solely being concerned with making the AI's say slurs. That's not their concern. But you can win any imaginary argument you like.

Likewise, people complaining that “AI safety concerns are just wokism gone wrong” are also strawmanning.

Re: Alpaca: A strong open-source instruction-following model

#95

Post by simonw »

bilsbie wrote: post #84
isaacfung wrote: post #57

Earlier quoted context omitted.

LLM just predicts the next token given the previous tokens(this can be trained without manual labelling by humans). Instruct GPT and ChatGPT use reinforcement learning from human feedback to align the model with human intents so it understands instructions. https://huggingface.co/blog/rlhf

Thanks. So what does the output look like without rlhf?

This comment has a useful comparison between the two: https://news.ycombinator.com/item?id=35140447

Re: Alpaca: A strong open-source instruction-following model

#96

Post by superkuh »

I've played a lot with davinci 3 ($25 of credits worth) and it can do some impressive rhyming and interpretation of concepts as emoji sequences. From the 3 times I've interacted with this fine tuned llama 7B it is clear it cannot do that. I've also run the "vanilla" 7B, 13B, and 30B on my home computer with llama.cpp modified for interactive "chat" mode with various pre-prompt and these can't do it either.

I have no love for openai/microsoft but their text completion davinci 3 really is incredible. I don't think these littler models have quite reached the point of emergence for some functions despite fine tuning.

Re: Alpaca: A strong open-source instruction-following model

#97

Post by beepbooptheory »

nlowell wrote: post #80
beepbooptheory wrote: post #52

Earlier quoted context omitted.

Its really just because of boring old liability, nothing more. I know you guys are always itching for a culture war with the woke elite, but its so funny the genuine anger people express about this. Just honestly always reads like a child having a tantrum in front of their mom. Can't yall like pick on the opinions of teenagers like you normally do? This very project shows you can make your own AI as edgy as you want…

You're missing the point and willfully characterizing others as solely being concerned with making the AI's say slurs. That's not their concern. But you can win any imaginary argument you like.

My favorite kind of comment: allude to a bigger point the op misses, but don't actually say the point.

I doubt I'm misrepresenting anybody. If its not slurs it's surely something about "wokeness."

You are not yet mature enough for this future if any of this is your concern. The world is going to pass you by while you're just stuck saying "there are only two genders" to all your comrades.

Don't let the politicians mobilize you like this, your time is worth more.

Re: Alpaca: A strong open-source instruction-following model

#98

Post by kir-gadjello »

azeirah wrote: post #92
bogwog wrote: post #31

Earlier quoted context omitted.

Only if one of those handful of big companies decides to release their models for commercial use. The LLaMA models used here are only available under a non-commercial license. Can’t build anything significant with leaked models. Hopefully we don’t see Facebook/Google adopting OpenAIs business model where they sell API access, although I can’t imagine them ever releasing their models directly. The last thing they woul…

Is there a reason why we aren't using BLOOM's model? It's huge, 160B parameters. It's open, it's free, it's been out there for a while. Is something wrong with it? Using outdated training data? Using outdated training techniques? Or is it just not well known enough -- ie, not in the news at the right time.

BLOOM, while being a useful model for underrepresented languages, underperforms openai's GPT-3 models of similar parameter count on english benchmarks. Which is a pity.

And OpenAI's known models (at least the ones for which the architecture is publicly known) https://platform.openai.com/docs/model-index-for-researchers aren't pinnacles of parameter efficiency either: Deepmind's Chinchilla and LLaMA beat them on benchmarks while being much smaller.

Just an opinion, but if we truly aim for "green computing" and carbon footprint reduction, we should pay a lot of attention to the parameter efficiency of the models that get run in our datacenters - and we should invest money into public availability of the most efficient foundation models.

Re: Alpaca: A strong open-source instruction-following model

#99

Post by valine »

bilsbie wrote: post #84
isaacfung wrote: post #57

Earlier quoted context omitted.

LLM just predicts the next token given the previous tokens(this can be trained without manual labelling by humans). Instruct GPT and ChatGPT use reinforcement learning from human feedback to align the model with human intents so it understands instructions. https://huggingface.co/blog/rlhf

Thanks. So what does the output look like without rlhf?

It can look like anything. Sometimes it will answer your questions, other times it will continue the question like its the one asking. I've also seen it randomly output footers and copyright like it just got to the end of a webpage.

Its makes sense when you think about how the training data is random text on the internet. Sometimes the most likely next token is the end of a webpage after an unanswered question.

Re: Alpaca: A strong open-source instruction-following model

#100

Post by mx20 »

Animats wrote: post #45
bryananderson wrote: post #4

Earlier quoted context omitted.

I am not a lawyer, but the consensus (around here anyway) seems to be that weights cannot be copyrighted since they are the output of an automated process, so perhaps the license cannot limit how the weights are used. The code can be copyrighted, but the code can also be reimplemented from scratch and used to load the weights.

The US doesn't have database copyright, but some countries, including the entire European Union, do.[1] [1] https://en.wikipedia.org/wiki/Database_right

Interesting. That could be a huge disadvantage for the EU and it's companies that want to use AI and also often can't give their Data to third parties. But I am not sure a neural net is even considered a DB. Because when this was created they clearly had structured Information accessed by people in mind. There has to be some distinction otherwise I make a db that stores digits of PI in a file and if you publish part of it, that is considered substantial enough, you are infringing on my DB rights.
Post reply on HN