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

DeciLM-7B: The Fastest and Most Accurate 7B-Parameter LLM to Date

deci.ai

Post reply on HN
Print view View original

31–40 of 45 posts

Re: DeciLM-7B: The Fastest and Most Accurate 7B-Parameter LLM to Date

#31

Post by moffkalast »

b33j0r wrote: post #27
nicce wrote: post #21

Earlier quoted context omitted.

Maybe it is written by the model itself.

Hah, the model is pretty good, but the material does sound like an American politician’s hype team. To be fair I think google and OAI are doing the same thing all the time: “As a large language model, I can explain. I and my relative were trained at the bestest universities, only in superlatives about humans who are optimum et vetustissimum octagenarium, i.e. the “bestest of all time! Could win nathan’s hot dog-eatin…

The best model in the history of models, maybe ever?

Re: DeciLM-7B: The Fastest and Most Accurate 7B-Parameter LLM to Date

#32

Post by nwoli »

blurpesec wrote: post #30
blurbleblurble wrote: post #28

Is anyone actually using these small models for general purpose applications? Or are they just used to fine tune into narrowly useful specialized models? I keep seeing them pass each other on different benchmarks and leaderboards and I can't help but imagine that so many of them are only good at benchmarks and not much else. I haven't gotten a chance to play with this stuff yet so I have no basis to go off of, but I'…

Mistral-7B is surprisingly decent for general purpose small tasks. The more complex the task or the more specific the knowledge recall, the worse the performance since the smaller the models are - the less breadth they tend to have. But they're very nice for making PoCs on complex systems since they're near free to run.

Have you tried the 0.2 version they released yesterday? Curious if you’re seeing significant improvements

Re: DeciLM-7B: The Fastest and Most Accurate 7B-Parameter LLM to Date

#33

Post by MyFirstSass »

blurpesec wrote: post #30
blurbleblurble wrote: post #28

Is anyone actually using these small models for general purpose applications? Or are they just used to fine tune into narrowly useful specialized models? I keep seeing them pass each other on different benchmarks and leaderboards and I can't help but imagine that so many of them are only good at benchmarks and not much else. I haven't gotten a chance to play with this stuff yet so I have no basis to go off of, but I'…

Mistral-7B is surprisingly decent for general purpose small tasks. The more complex the task or the more specific the knowledge recall, the worse the performance since the smaller the models are - the less breadth they tend to have. But they're very nice for making PoCs on complex systems since they're near free to run.

There's even a new version of the Mistral 7b out there today that should be a lot better, v 0.2.

The finetunes of 0.1 are already extremely impressive at general tasks.

https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGU...

Re: DeciLM-7B: The Fastest and Most Accurate 7B-Parameter LLM to Date

#34

Post by MyFirstSass »

that_guy_iain wrote: post #25
wantsanagent wrote: post #20

The language in this blog post is overblown to say the least. "groundbreaking", "outshines its competitors", "remarkable", "pivotal transformation" Totally unnecessary bravado.

Why is it that so many people here have to comment on basic marketing stuff? It is necesssary bravado because it's trying to convince people that it's worth using. And saying "Here is a model that is just a bit better than others" isn't going to do anything. Therefore it's necessary to have buzzwords such as groundbreaking.

Mistral is doing the exact opposite and everyone is talking about it.

I'll never respect marketing like this because it's standing on the shoulders of thousands of others peoples work.

Re: DeciLM-7B: The Fastest and Most Accurate 7B-Parameter LLM to Date

#35

Post by moffkalast »

petesergeant wrote: post #24
MyFirstSass wrote: post #22

Their website looks like buzzword bingo from the crypto days with no substance whitepapers and a big group of "researchers" + lots and lots of cool graphics and a huge money making "platform" before they have a product. "Book a demo" lmao. The literal opposite of Mistral's "no marketing" just a torrent with the data. Off course it may be actual new work but colour me very sceptical with this extreme confidence and ma…

Sure, but a crucial difference here is you can go right now and try it out and see if it's garbage or not on HuggingFace[0] 0: https://huggingface.co/spaces/Deci/DeciLM-7B-instruct

> I put a plate on a banana in the kitchen, then take the plate to the living room. Where is the banana?

> The banana is still in the kitchen, as it was placed on the plate before it was moved to the living room.

He's a little confused, but he's got the spirit.

Re: DeciLM-7B: The Fastest and Most Accurate 7B-Parameter LLM to Date

#37

Post by nwhitehead »

blurbleblurble wrote: post #28

Is anyone actually using these small models for general purpose applications? Or are they just used to fine tune into narrowly useful specialized models? I keep seeing them pass each other on different benchmarks and leaderboards and I can't help but imagine that so many of them are only good at benchmarks and not much else. I haven't gotten a chance to play with this stuff yet so I have no basis to go off of, but I'…

I'm using the new generation of small models to do semantic search for music lyrics. The first step is giving the model the text and asking, "What is this text about?" Without fine-tuning and only minimal prompt engineering these models can understand most languages, pull out the most relevant phrases, and list major themes and speculative ideas of what the lyrics mean. I'm super impressed with the results. Reading the answers feels like grading ambitious undergraduate student essays (both the good and the bad).

Re: DeciLM-7B: The Fastest and Most Accurate 7B-Parameter LLM to Date

#38

Post by ekianjo »

wantsanagent wrote: post #20

The language in this blog post is overblown to say the least. "groundbreaking", "outshines its competitors", "remarkable", "pivotal transformation" Totally unnecessary bravado.

Marginally better just because it does less poorly at math problems. Meh.

Re: DeciLM-7B: The Fastest and Most Accurate 7B-Parameter LLM to Date

#39

Post by davidkunz »

blurbleblurble wrote: post #28

Is anyone actually using these small models for general purpose applications? Or are they just used to fine tune into narrowly useful specialized models? I keep seeing them pass each other on different benchmarks and leaderboards and I can't help but imagine that so many of them are only good at benchmarks and not much else. I haven't gotten a chance to play with this stuff yet so I have no basis to go off of, but I'…

Yes, I'm using them in my text editor with my plugin [1] and it's already useful for everyday tasks like summarization, fixing grammar or making text more concise.

[1]: https://github.com/David-Kunz/gen.nvim

Re: DeciLM-7B: The Fastest and Most Accurate 7B-Parameter LLM to Date

#40

Post by osmarks »

blurbleblurble wrote: post #28

Is anyone actually using these small models for general purpose applications? Or are they just used to fine tune into narrowly useful specialized models? I keep seeing them pass each other on different benchmarks and leaderboards and I can't help but imagine that so many of them are only good at benchmarks and not much else. I haven't gotten a chance to play with this stuff yet so I have no basis to go off of, but I'…

I use the Mistral-7B base model for a few things via fewshot prompts, but not really for anything production, just some fun toys.
Post reply on HN