[HN Gopher] Open source implementation for LLaMA-based ChatGPT
       ___________________________________________________________________
        
       Open source implementation for LLaMA-based ChatGPT
        
       Author : georgehill
       Score  : 253 points
       Date   : 2023-02-27 14:30 UTC (8 hours ago)
        
 (HTM) web link (github.com)
 (TXT) w3m dump (github.com)
        
       | voytec wrote:
       | Fake title riding on ChatGPT popularity. I think that it should
       | be updated to something like:
       | 
       | Open source implementation for LLaMA-based chat bot*
       | 
       | Open source implementation for LLaMA-based ChatGPT alternative*
        
         | agolio wrote:
         | I think the 'alternative' is implied
        
       | threevox wrote:
       | Can someone leak the weights please
        
       | bethecloud wrote:
       | open-assistant from LAION is in the process of creating an OSS
       | RLHF dataset for a personal assistant, may be useful for this
       | project
        
       | davidy123 wrote:
       | I am very far from an expert on this, but I think domain specific
       | conversational AI would be much more useful than these large
       | models. It's fun to ask an AI to compose a fresh 600bpm hip hop
       | song about the relationship between materials science and the
       | breeding habits of mosquitoes, but an open-source medical AI,
       | application support AI, or many other applications would be much
       | more practical, if they could be accurate enough. And especially
       | if they could run "standalone." They could also consult with each
       | other, as a network of specialized AI. Is work inching closer to
       | more specific, more accurate applications? Or is this just a big
       | gimmick/distraction phase around a maybe not so great idea of AI?
        
         | Taek wrote:
         | These models are only capable of coherent conversation in the
         | first place because they are so large. As soon as you shrink it
         | down to be 'domain specific' its ability to form coherent
         | sentences even within its own domain greatly reduces.
        
         | pmarreck wrote:
         | I think you would still need a large model to train on general-
         | purpose knowledge and then train on domain specific things to
         | get the specialized knowledge to be truly useful. For example,
         | without a general-purpose model, if someone wanted domain-
         | specific language "translated" for a neophyte, I doubt it would
         | be able to without having also been trained on a general-
         | purpose dataset
        
         | nfgrep wrote:
         | The way its typically done, AFAIK, is that you train these big
         | models on a breadth of information, hoping that it picks up on
         | the generalities of the information. In the case of LLMs,
         | things like basic inference, for example. You then take these
         | big, general models and "fine tune" them for specific
         | applications, with specific bits of data. This way, you get
         | things like basic inference, and logic, while still having
         | something that can answer specific questions.
         | 
         | OpenAI offers the ability to fine-tune some of their models:
         | https://platform.openai.com/docs/guides/fine-tuning
         | 
         | There are also other services that will fine-tune an LLM, for a
         | specific domain, for you: https://activechat.ai/build-your-own-
         | chatgpt/
        
         | Thebroser wrote:
         | There are definitely very solid attempts at least to make LLMs
         | that encode biomedical knowledge such as BioGPT which is
         | trained on Pubmed and other domain specific areas. Source:
         | https://arxiv.org/abs/2210.10341
        
         | PeterisP wrote:
         | My opinion is entirely opposite - we need conversational AI for
         | exploring the multitude of possibilities and identify what
         | works, what doesn't work, what is/isn't useful given the
         | obvious limitations on accuracy, truthfulness and
         | interpretability; but once we can identify a specific narrow
         | use case then we can fine-tune a ML system for that isn't
         | conversational but is able to provide better results with
         | whatever domain-specific structure is required (linking to
         | specific sources, including external structured data, providing
         | certainty metrics, filtering results according to domain-
         | specific criteria instead of the conversational political
         | correctness filters which fail some domains, treatment info
         | which was correct but has become outdated, etc, etc) that can
         | be done better in non-conversational systems.
        
           | panarky wrote:
           | The P in GPT is for "pretrained".
           | 
           | The large pretrained model is a prereq for domain-specific
           | models.
        
             | PeterisP wrote:
             | Not necessarily, you don't need to make a domain-specific
             | model from a general model, you can definitely make a large
             | pretrained domain-specific model from scratch by training
             | it only on domain-specific data, which can result in a
             | smaller and more efficient model.
             | 
             | Furthermore, when making task-specific models, an 'encoder'
             | architecture (similar to BERT) often works better than a
             | 'decoder' architecture (similar to GPTx), so you might want
             | to use a similar-but-different architecture than the
             | general model intended to be conversational/generative.
        
               | panarky wrote:
               | If you want to build a domain-specific classifier that
               | determines whether an image is a dog or a cat, and you
               | have 50 labeled images of dogs and cats, it's much better
               | to start with a large model pretrained on millions of
               | images, and then specialize it by training on 50 images
               | of dogs and cats.
               | 
               | Try to start with a NN and 50 images of dogs and cats,
               | and it won't work very well.
        
               | PeterisP wrote:
               | Sure, that's correct, but that's absolutely unrelated to
               | what we were talking about; your example is about the
               | general concept of transfer learning to task-specific
               | annotated data, not about domain-specific pretrained
               | models.
               | 
               | For example, if you want a domain-specific model for the
               | legal domain, then you can pre-train a large self-
               | supervised model on every single legal-related document
               | in the world you can get your hands on, instead of a
               | general mix of news and fiction and blogs and everything
               | else - and that might be a more efficient starting point
               | for however many(few) annotated examples you have for
               | your task-specific classifier than the general model.
        
               | panarky wrote:
               | Legal-related documents are a minuscule fraction of the
               | corpus the large model is trained on. The resulting model
               | won't have the conceptual fluency that the large model
               | has. It's like training a human baby with legal briefs
               | and expecting her to be a good lawyer.
        
         | og_kalu wrote:
         | Smaller models are typically dumber. Sure you could fine-tune a
         | smaller model on say the medical domain and they might even
         | perform better on some benchmarks but they won't reason or
         | generalize as well. domain finetuned large models >>> domain
         | finetuned small models. And because competence in one area
         | bleeds over to other areas, you often need much less domain
         | specific data to finetune on compared to the smaller models.
         | 
         | You can see instances of this with Minerva, where the finetuned
         | 540b version beats the finetuned 62b version despite being
         | finetuned on only a quarter of the data the 62b version was
         | finetuned on.
        
           | muttled wrote:
           | They're claiming the 13b model beats GPT-3 175b which is an
           | extraordinary claim requiring extraordinary evidence. If
           | that's true, though, it'd be interesting to see if that also
           | applies to fine-tuning. Since the claim is predicated on the
           | 13b model being better trained (amongst other things?), I
           | wonder if limited fine-tuning data handicaps the 13b model
           | even if the base model can outperform GPT-3 Davinci, given
           | your point about large models handling fine-tuning better
           | with limited data.
        
             | og_kalu wrote:
             | I mean the benchmarks are there. Can't exactly fake that.
             | It should apply to fine-tuning. fine-tuning works off the
             | back of the weights. That's why instruction-finetuned
             | models even of small models like the T5 converge much
             | faster on any additional fine-tuning or training than their
             | non instruct counterparts as per the flan paper. Honestly,
             | what i'm taking from this paper is that even chinchilla is
             | undertrained. 13B was trained on 1T tokens.
        
         | visarga wrote:
         | You can already do that. Take your task first to GPT-3 and
         | collect a bunch of outputs. Then fine-tune a small model on
         | them. Works well, but you need to extend the dataset to cover
         | all edge cases because the small model can't draw on the vast
         | knowledge GPT-3 has.
        
       | amrb wrote:
       | I would care more about LLaMA architecture when I can get hands
       | on, honestly this project is more interesting and lighting fast
       | on even a 2060 laptop https://github.com/BlinkDL/RWKV-LM
        
         | la64710 wrote:
         | News flash : filling a google form to get access to the model
         | based on Meta's discretion cannot be called open source .
        
           | MH15 wrote:
           | And yet they're trying real hard to.
        
         | iForgotMyPW wrote:
         | came here to say this
        
         | nl wrote:
         | > I would care more about LLaMA architecture when I can get
         | hands on
         | 
         | The architecture is available just fine, both in the paper[1]
         | and in code:
         | https://github.com/facebookresearch/llama/blob/main/llama/mo...
         | 
         | It's the model weights that you can't get as easily.
         | 
         | [1] https://research.facebook.com/publications/llama-open-and-
         | ef...
        
         | UncleOxidant wrote:
         | The README there doesn't seem too coherent... how does one
         | actually get that running? The Quick Start section isn't very
         | helpful.
        
         | lachlan_gray wrote:
         | Has anyone tried this on an m1 machine?
        
           | tmptmptmp1 wrote:
           | Do you have access to the weights? If so you probably have
           | better ML hardware. Wish this model was actually "open".
           | 
           | The perf of a model of that size on the M1 will not be good.
           | That is big enough it won't quite fit on a 3090 (24GB)
           | without quantization.
        
           | pumanoir wrote:
           | I think is feasible. The description even says is designed to
           | save on vram[1]. I don't get the other comments about needing
           | more vram than a 3090.
           | 
           | Also, Neuralmagic may run their sparsification on ARM cpu's
           | in the future, so keep an eye.
           | 
           | 1. _ChatRWKV v2: with "stream" and "split" strategies. 3G
           | VRAM is enough to run RWKV 14B :)_
        
           | fswd wrote:
           | I've ran it on a AMD 3950 which I think is half the speed of
           | a M1, and it's plenty fast. Note I am specifically talked
           | about RWKV
        
         | dwheeler wrote:
         | The nebullvm projrct and specifically chatllama, by themselves,
         | are clearly OSS. They're licensed under Apache-2.0:
         | https://github.com/nebuly-ai/nebullvm/tree/main/apps/acceler...
         | 
         | However, many models including LLaMA are _not_ OSS (they have
         | terms such as  "non-commercial use only"). And you need models.
         | 
         | It can be confusing, it's important to try to make that clear.
        
         | pmarreck wrote:
         | very interesting. Do you know of anything that would take
         | advantage of the 128 cores of my Ryzen Threadripper even though
         | I have a 2080 and a 3080 as well? (Or all three... lol)
        
           | vorticalbox wrote:
           | GPU is massively faster than CPUs for this sort of work load.
           | 
           | Even if you could use all 128 cores I would still get the
           | 2080 would be faster
        
             | zackmorris wrote:
             | Keep in mind that many of the GPU cores go unused, since
             | they are dedicated to geometry or ray tracing or whatnot:
             | 
             | https://www.pcworld.com/article/402592/nvidia-turing-gpu-
             | gef...
             | 
             | IMHO these chips designed for specialized workloads are
             | looking more and more ridiculous. I expect GPU
             | manufacturers to keep dragging them out for another decade
             | or so, as well as Apple as it explores offshoots of M1. It
             | all makes me feel very tired (the ultimate code smell).
             | 
             | A better design would be something like a 256+ core RISC-V
             | with local memories in/by each core for data-locality and a
             | content-addressable caching scheme for deduplication. Copy-
             | on-write languages like Clojure and orchestrating processes
             | under something like Docker would make it a breeze to
             | program, although it would still support manually managed
             | mutability like with Rust for innermost loops in games or
             | whatever. It's fairly obvious how it would all work, but IP
             | law and gatekeeping ensure that it will not happen anytime
             | soon.
             | 
             | Then stuff like CUDA would be just another framework run on
             | a symmetric multiprocessor and we could get back to
             | exploring alternatives like genetic algorithms like we did
             | in the 1990s. Thankfully nobody cares what I think, heck
             | even I'm sick of reading my own complaints, so it's easy
             | enough to just unsee this.
        
               | dragonwriter wrote:
               | > Keep in mind that many of the GPU cores go unused,
               | since they are dedicated to geometry or ray tracing or
               | whatnot
               | 
               | I mean, "many" is not usually the case; an RTX 3090 has
               | 10,496 CUDA cores, 328 Tensor cores, 82 RT (raytracing)
               | cores, and 96 render output pipelines. ML apps will uses
               | the first and, depending on software, second set. The
               | vast majority of the cores being CUDA cores is the norm.
        
             | pmarreck wrote:
             | ah ok, that's fair.
        
             | zamalek wrote:
             | This is not strictly true. GPUs fare better at these tasks
             | for a few reasons:
             | 
             | * The largest contributor is the sheer number of cores.
             | 
             | * The latency between cores and memory.
             | 
             | * FP16 instructions.
             | 
             | 128 cores isn't an insignificant fraction of the number of
             | cores on a 1050 (about 600), but CPU cores are individually
             | more powerful. That advantage is potentially difficult to
             | call. The top-end of Genoa has 96/192 cores, and you can
             | slot many of them onto a single board.
             | 
             | AMD is throwing more and more memory into the CPU cache.
             | That's very different to a direct path to GBs of HBM, but
             | at some point the difference in performance might not
             | matter to a novice/dabbler.
             | 
             | I would say give it a go, see what happens.
        
           | amrb wrote:
           | There is an example to use multi GPU in the link, Outside of
           | this I have read about offloading to cpu/nvme in the case of
           | 100GB+ models that don't fit in VRAM tho this will be at the
           | expense of performance.
           | 
           | https://pypi.org/project/rwkvstic/
        
           | qwertox wrote:
           | I'm using a Ryzen 9 5950X to run some tests with Whisper
           | (ASR), and since I have no GPU with more than 4 GB VRAM, I'm
           | running it on the CPU. It is slow. It takes between 20
           | seconds and 2 minutes to transcribe 1 minute of audio, I'm
           | using 8 cores. Adding more cores doesn't seem to improve the
           | inferencing time.
           | 
           | ML is really something which should be left to a GPU.
        
           | pumanoir wrote:
           | Look into sparsification of ML models:
           | https://neuralmagic.com/ If your cpu has avx512 it can make
           | it even faster.
        
       | shmatt wrote:
       | I don't really understand the benchmarking aspect researchers are
       | touting. The public never cared about LLMs until they had a
       | proper conversation with one. You can beat GPT3 at any benchmark
       | you'd like, but if you can't get people that "feeling" when
       | chatting with your model, is it worth anything?
       | 
       | In the future there's going to have to be a way to benchmark the
       | "human-ness" or "intrigue" or "feistiness" of a model to show us
       | if its getting better at what we want
        
         | antoineMoPa wrote:
         | I guess one technique is to train a model on various language
         | model outputs to classify these as good/bad/intriguing/robot-
         | sounding/repetitive/etc. A human can tag the answers for the
         | training dataset.
         | 
         | Then, we can use this model to compare different LLMs and
         | optimize new models - could be with genetic algorithms or just
         | a human tweaking the model - so that the LLM maximizes whatever
         | we want.
        
           | visarga wrote:
           | You just rediscovered RLHF - reinforcement learning from
           | human preferences. That's the last stage of training for
           | chatGPT, but uses RL instead of supervised learning.
        
         | basch wrote:
         | The question is, where does this "human-ness" lie? In the
         | initial neural network, the training data, or the supervised
         | reinforcement?
         | 
         | In theory, a significantly smaller neural network that outputs
         | at nearly as good a quality, should be able to chew through
         | training data, and its re-enforcement process, much faster and
         | cheaper, right? A more generalized, lower parameter model, is
         | almost always preferred, as long as it works?
         | 
         | If the human feeling is all boltonable to the neural net later,
         | there is no reason to discount this component as lacking
         | potential to exceed current models.
        
           | visarga wrote:
           | I think it's the feedback from RLHF that is mostly
           | responsible, but it only works if the base model is large.
           | Never seen a small model doing good conversation. They can do
           | ok for classification and open book question answering, but
           | generating long form coherent text is hard.
        
         | skybrian wrote:
         | Often articles show up on Hacker News that are meant for other
         | researchers, not the general public. Not everything is a
         | product.
         | 
         | Benchmarks are used as a way to show that a particular machine
         | learning technique does better at some task. It's a way for
         | researchers to show they're making progress that will be
         | legible to other researchers. You can't publish a paper saying
         | "we tried it out and we think it's better."
        
         | dragonwriter wrote:
         | The techniques to go from a basic GPT-like model to a
         | conversational agent are largely published and should be
         | reproducible, open-source base models are starting points for
         | that work that are unencumbered and available.
         | 
         | This is important for researchers and implementers, not
         | (immediately, ay least) end users.
        
         | rnosov wrote:
         | GPT-3 performed really well on synthetic benchmarks. It was
         | later made palatable for general public consumption. You might
         | say that a LLM needs to be good on synthetic benchmarks first
         | before you can make public facing chatbots with it.
        
       | visarga wrote:
       | This whole debate - if a 13B model can really be as good as GPT3
       | - would have been settled if we had a live demo. I am not sure
       | their licence allows running public demos, even if you get the
       | weights.
        
       | rnosov wrote:
       | Looks like they are making ChatGPT clone that would be possible
       | to run a single GPU. HN dream come true!
        
         | swyx wrote:
         | lol good luck running a 13B model on a single GPU
        
           | ddren wrote:
           | Seeing the performance of implementations like FlexGen [1], I
           | don't think it would be entirely unreasonable to run a 13B
           | model on a single GPU for personal usage purposes. You are
           | not going to a run a public service out of it, but it
           | probably would be good enough to run your own ChatGPT or
           | Copilot locally.
           | 
           | [1]: https://github.com/FMInference/FlexGen
        
           | visarga wrote:
           | You need a RTX 3090 24gb
        
         | wcarss wrote:
         | ChatGPT's stable diffusion moment?
        
           | Taek wrote:
           | Can't have a stable diffusion moment if you refuse to release
           | the weights to the general public. Stable diffusion only got
           | to where it is because 10,000 people with otherwise zero
           | reputation were able to play around with the code and models.
           | 
           | LLaMA is still only available to the elite.
        
       | Jack5500 wrote:
       | This seems like a great first step to a truly open source LLM
        
         | visarga wrote:
         | If we can confirm the 13B model is as good as GPT3 then at
         | least we have a target for reproduction without FB
         | restrictions.
        
         | lurquer wrote:
         | Indeed. All the weights for all the models will be available
         | one way or the other very soon.
         | 
         | The proprietary nature of the weights is not going to be a
         | bottleneck for more than a month, if I had to guess.
         | 
         | The other bottle-neck to personal use -- the hardware required
         | to run (not train from scratch) the thing - is going to be gone
         | within the year I bet. I would assume some clever bloke is
         | going to be able to prune the model or decrease the precision
         | of the weights and discover you can get good-enough results
         | with 1/10th of the memory.
         | 
         | What happens then?
         | 
         | Well, probably some Very Bad Things.
        
       | agolio wrote:
       | I'm as much a META hater as anyone - their policies have
       | consistently disappointed me in almost every aspect of their
       | business - but their stance on this LLaMA project I must say I am
       | happy with and seems to mark a turn for the better.
       | 
       | If they follow through on their promise of making the weights
       | available and share source code that is a big step in the right
       | direction for democratising this technology
        
         | cuuupid wrote:
         | The weights are non commercial and while their code is GPLv3
         | they've only released inference and have removed anything that
         | would give away the training methods :)
        
           | alfalfasprout wrote:
           | The paper highlights the training methods pretty clearly
           | though including what tweaks they made.
        
         | A4ET8a8uTh0 wrote:
         | Yeah, but their history ( and accumulated goodwill ) are
         | similar to Microsoft's. They may say it is 'open' or sprinkle
         | appropriately sounding corporate speaking all over the press
         | release, but the actions will, at best, temporarily prevent
         | them from going 'full evil ahead'.
         | 
         | And I like that announcement. I just don't think they will
         | actually follow through on this.
        
           | visarga wrote:
           | Yann LeCun, who is director of AI research at FB is all over
           | the ML Twitter talking about this model. I think they will
           | actually release the weights.
        
             | ilaksh wrote:
             | When? Why didn't they release them already?
        
       | georgehill wrote:
       | For anyone wondering what LLaMA is, here are some useful links.
       | 
       | https://ai.facebook.com/blog/large-language-model-llama-meta...
       | 
       | https://news.ycombinator.com/item?id=34925944
        
         | swyx wrote:
         | those who know what it is are questioning why you are working
         | on this when the base model itself is not released widely.
         | whats the intention here?
        
           | georgehill wrote:
           | i am not the author of the repo, i came across this on
           | github.
           | 
           | https://twitter.com/nebuly_ai is the author of the repo.
        
       | levesque wrote:
       | In what way is this a ChatGPT implementation or equivalent? Seems
       | like a chatbot based on a different backend, therefore it has
       | absolutely zero link to ChatGPT.
        
         | basch wrote:
         | It is an analogy.
         | 
         | ChatGPT:GPT3::ChatLLaMa:LLaMa
        
           | levesque wrote:
           | It uses a different engine, so this is as related to ChatGPT
           | as a Toyota Corolla is related to a BMW car. This is an
           | efficient and open-source chatbot, which is very good news,
           | but the authors just wrote a clickbait title and they know
           | it.
        
             | f_devd wrote:
             | > Toyota Corolla is related to a BMW car.
             | 
             | The analogy is somewhat accurate, but also moot, since
             | within the ML community "ChatGPT" can be used either as the
             | product or the method (more specifically called RLHF)
             | somewhat interchangeably. It's more like Google/Googling,
             | where the largest/most popular provider becomes the defacto
             | way to refer to a method. As someone who develops DL
             | models, the title seems quite apt.
        
             | basch wrote:
             | In formal analogies, : is pronounced "is to" and :: is
             | pronounced "as".
             | 
             | The purpose here is to use the relationship from a known,
             | to describe the relationship between a partial known.
             | 
             | ChatGPT is to GPT3 as ChatLLaMa is to LLaMa. It uses the
             | relationship between ChatGPT and GPT3 to extrapolate a
             | relationship between an unknown and LLaMa.
             | 
             | see Analogies.pdf https://resources.finalsite.net/images/v1
             | 584287027/brockton/...
             | 
             | Corolla:Toyota::3-Series:BMW. If you had heard of a
             | Corolla, Toyota, and BMW, but not a 3-Series, you now
             | roughly know that a 3-Series is BMWs equivalent to a
             | Corolla.
        
               | levesque wrote:
               | I think I prefer the other commenter's point, referring
               | to ChatGPT as a known learning paradigm for chatbots. But
               | thanks for the little crash course on analogies ;)
        
               | basch wrote:
               | Isn't that consistent with, and the same as, my original
               | comment?
               | 
               | ChatGPT:GPT3::ChatLLaMa:LLaMa::Chatbot-through-RLHF:LLM
               | 
               | aka ChatGPT is a known chatbot implementation, and GPT3
               | and LLaMa are known LLMs.
        
               | levesque wrote:
               | Yes and no. You wouldn't say GPT to mean large language
               | models or autoregressive language models. I would've
               | thought the same to be true for ChatGPT instead of
               | Chatbots with RL from human feedback (RLHF), perhaps the
               | field is moving towards adopting ChatGPT as a paradigm
               | name. Note that the title doesn't say a ChatGPT-like
               | model based on LLaMa, it says outright opensource
               | implementation of ChatGPT.
        
               | basch wrote:
               | > You wouldn't say GPT to mean large language models or
               | autoregressive language models.
               | 
               | In the analogy, that's exactly what you are saying.
               | Identical to Toyota and BMW meaning "the make of the
               | car."
               | 
               | Maybe reimplementation is a more precise word, a black
               | box re-engineering/cloning. In this case I inferred it by
               | knowing it was a different LLM underneath, and that this
               | group didn't have access to the chatgpt source code.
        
         | rnosov wrote:
         | It is a different backend but it supposedly should be roughly
         | comparable to ChatGPT. Also, looks like it's both open source
         | and requires a lot less hardware to run and train.
        
           | Taek wrote:
           | Its not open source until the weights are available. I have
           | the hardware I need to run it but the required files are not
           | available unless you receive special access.
           | 
           | You can't use what has been released unless you want to spend
           | $500,000 on training.
        
             | pmarreck wrote:
             | With only a modicum of trolling-level here, I wonder what
             | percentage of that training expense was used to identify
             | and avoid "true things that must be muted because they
             | offend someone"
        
       | karmasimida wrote:
       | Is it of any good?
        
       | rvz wrote:
       | > LLaMA is creating a lot of excitement because it is smaller
       | than GPT-3 but has better performance. For example, LLaMA's 13B
       | architecture outperforms GPT-3 despite being 10 times smaller.
       | 
       | Exactly. Best part is that it is open-source.
       | 
       | That is worth getting excited about. Not a AI SaaS API owned by a
       | so-called pseudo-non profit company which struggles on API uptime
       | and availablity, just like GitHub.
       | 
       | This is the 'revolution' you are looking for that changes
       | everything. Not ChatGPT.
        
         | Ozzie_osman wrote:
         | Is it open source though? It looks like Meta was only releasing
         | it to academics who apply.
        
         | Taek wrote:
         | its not open source, only approved researchers are allowed to
         | access the weights. More ivory towering from the AI industry.
        
           | mikie92 wrote:
           | right, and I guess there'll be opensource alternatives of
           | llama very soon
        
           | eigenvalue wrote:
           | It's for your own "safety"...
        
       | holtkam2 wrote:
       | I don't have a decent gpu at my disposal... has anyone tried to
       | run LLaMA on an EC2 GPU instance? If so, which instance type? (I
       | don't wanna overpay)
        
         | alfalfasprout wrote:
         | Per the paper the 13B variant runs on a single A100 GPU.
        
       | jstsch wrote:
       | Are LLaMA's weights generally available/floating around yet?
        
         | gavi wrote:
         | I think you need to apply for it @Meta
         | 
         | https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z...
        
         | amrb wrote:
         | Nope they pulled a fast one and limited it to academy and
         | government, just put the dam thing on hugging face like
         | everyone else guys..
        
           | swyx wrote:
           | piratebay, but for model weights
        
       | didntreadarticl wrote:
       | Have we got any details on the benchmarks that show LLaMa's 13B
       | architecture outperforming GPT-3? Because that seems kindsof
       | fantastical. Is it just a product of a very specific benchmark or
       | does it reflect real world performance?
        
         | rafaelero wrote:
         | The GPT-3 they are comparing to is the one that was released on
         | 2020. Since then OpenAI made a lot of improvements and nowadays
         | I believe GPT-3.5 is competitive to Palm (540b). Still, LLaMa
         | is in the same tier, with much less parameters.
        
           | og_kalu wrote:
           | Just a heads up with my comparison. Under equivalent
           | scenarios, the gap is smaller. davinci-003 gets about 10 more
           | points using five shot (which is what the palm comp does)
        
           | og_kalu wrote:
           | GPT 3.5 is definitely not comparable to Palm. You can see
           | some benchmarks here.
           | https://crfm.stanford.edu/helm/latest/?group=core_scenarios
           | For example, text-davinci-3 is 56.9 on MMLU, Flan-Palm is 75.
           | https://arxiv.org/abs/2210.11416
        
             | tikkun wrote:
             | Flan-Palm is 75 with five-shot. text-davinci-003 is it 56.9
             | with five-shot or zero-shot?
        
               | og_kalu wrote:
               | You're right. Equivalent scenarios, the gap is smaller -
               | about a difference of 10. you can check the end of the
               | flan paper for some equivalent comparisons.
        
         | rnosov wrote:
         | They list 7B, 13B, 33B, 65B architectures. Presumably, they
         | compare 65b one to GPT-3 175B. Chinchilla model which is about
         | 70B outperformed a much larger GPT-3 model. So not that
         | fantastical.
         | 
         | EDIT: I stand corrected. They do compare 13B model with a large
         | GPT-3 model which is hard to believe without a bit more
         | concrete evidence
        
           | rileyphone wrote:
           | You're incorrect.
           | 
           | > For example, LLaMA's 13B architecture outperforms GPT-3
           | despite being 10 times smaller.
           | 
           | Of course this is all on benchmarks but it's a big
           | improvement if true.
        
       | gersh wrote:
       | Is the trained model available to download anywhere?
        
         | ddren wrote:
         | Not really, the LLaMA model is only available on request and
         | access is granted on a "case by case basis" [1], which for most
         | of us is more or less as available as GPT-3 is.
         | 
         | [1] https://ai.facebook.com/blog/large-language-model-llama-
         | meta...
        
           | swyx wrote:
           | > more or less as available as GPT-3 is
           | 
           | what? GPT3 is available by a public api that anyone can sign
           | up and pay for and use for commercial use. how is it "as
           | available"?
        
             | ddren wrote:
             | I was mostly talking about access to the trained model
             | weights. The OpenAI API is certainly better than nothing,
             | but it is very restrictive and cost prohibitive for many
             | purposes. For instance, you have to adhere to the OpenAI
             | usage policies, and while they offer fine-tuning services,
             | it is not likely enough to implement techniques like RLHF,
             | which is the basis for ChatGPT.
             | 
             | That said, if LLaMa can achieve performance competitive
             | with GPT-3 with just 13B parameters, I imagine that it is
             | only a matter of time until open source pre-trained models
             | based on this architecture become available, which would
             | render GPT-3 obsolete.
        
       | SakiWatanabe wrote:
       | What is the purpose of this? The model from meta is not available
       | to public. Neither this open source "LLaMA-based ChatGPT" nor the
       | "open source" LLaMA can be downloaded or actually used by public
       | because it would required the actual trained model.
        
         | swyx wrote:
         | also LLaMA was released like 2 days ago - how far in advance
         | did these folks know about it?
        
           | vdfs wrote:
           | At least 2 days for sure
        
       ___________________________________________________________________
       (page generated 2023-02-27 23:02 UTC)