Open source implementation for LLaMA-based ChatGPT

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 <a href="https:&#x2F;&#x2F;github.com&#x2F;BlinkDL&#x2F;RWKV-LM">https:&#x2F;&#x2F;github.com&#x2F;BlinkDL&#x2F;RWKV-LM</a>

I don&#x27;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&#x27;d like, but if you can&#x27;t get people that &quot;feeling&quot; when chatting with your model, is it worth anything?<p>In the future there&#x27;s going to have to be a way to benchmark the &quot;human-ness&quot; or &quot;intrigue&quot; or &quot;feistiness&quot; of a model to show us if its getting better at what we want

What is the purpose of this? The model from meta is not available to public. Neither this open source &quot;LLaMA-based ChatGPT&quot; nor the &quot;open source&quot; LLaMA can be downloaded or actually used by public because it would required the actual trained model.

I&#x27;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.<p>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

For anyone wondering what LLaMA is, here are some useful links.<p><a href="https:&#x2F;&#x2F;ai.facebook.com&#x2F;blog&#x2F;large-language-model-llama-meta-ai" rel="nofollow">https:&#x2F;&#x2F;ai.facebook.com&#x2F;blog&#x2F;large-language-model-llama-meta...</a><p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=34925944" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=34925944</a>

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&#x27;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 &quot;standalone.&quot; 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&#x2F;distraction phase around a maybe not so great idea of AI?

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.

Have we got any details on the benchmarks that show LLaMa&#x27;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?

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.

Looks like they are making ChatGPT clone that would be possible to run a single GPU. HN dream come true!

Fake title riding on ChatGPT popularity. I think that it should be updated to something like:<p>Open source implementation for LLaMA-based chat bot*<p>Open source implementation for LLaMA-based ChatGPT alternative*

I don&#x27;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&#x27;t wanna overpay)

Are LLaMA&#x27;s weights generally available&#x2F;floating around yet?

open-assistant from LAION is in the process of creating an OSS RLHF dataset for a personal assistant, may be useful for this project

Can someone leak the weights please

This obsession with <i>locking up</i> model weights behind a gate-keeping <i>application form</i> and calling it <i>open source</i> is weird. I don&#x27;t know who the high priests are trying to fool.<p>If your model is really that good, unleash it into the open so that others can truly evaluate it-warts and all-and help improve it by identifying the flaws.

The difference between invention &amp; innovation is that innovation is when you ship your product to the masses. Can I query llama in a line of code? No

Is the trained model available to download anywhere?

&gt; LLaMA is creating a lot of excitement because it is smaller than GPT-3 but has better performance. For example, LLaMA&#x27;s 13B architecture outperforms GPT-3 despite being 10 times smaller.<p>Exactly. Best part is that it is open-source.<p>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.<p>This is the &#x27;revolution&#x27; you are looking for that changes everything. Not ChatGPT.

Is it of any good?

This seems like a great first step to a truly open source LLM