rajko_rad

wow, I'm not a bio person and had no idea AlphaFold was so complex compared to vanilla Transformers, etc. I wonder newer combinations of LLMs with RL for general reasoning are looking like, sad we might never know haha, but can dive into this in the interim :)

that is the only place they launched, no blog post or anything like that on the website!

Ah yes it’s working now… let me just resubmit, thank you :))

Thanks for the flag !

The actual announcement link wasn’t working an hour ago when we posted it, so we decided as a next best option to post the tweet :/

Appreciate the flag again and thank you for your patience with us here :)

We would love your feedback and contributions! We would also love to hear your thoughts on the future of AI Agent architectures and approaches like those we are building on top of with TreeVoyager! Also feel free to reach out to Marco/Matt if you have any Qs on using the playground to test your agents!

Honored to have you in the inaugural cohort @jph00!!

Awesome suggestions, thank you!

we didn't buy a condo haha, are letting people choose their own housing :)

thanks so much - we agree!

honestly would recommend using spot/rented instances on that budget vs. buying! A100s run around ~$2/hour, the hard part is getting a large allocation... training workloads are quite spikey anyways, usually running lots of smaller experiments before actually doing a larger single run...

feel free to DM on twitter or linkedin. In a nutshell, if you want to pursue a company now in or in the near future, we would likely need to consider you through our normal investing process for equity funding. If you are considering just working on it OSS, we would encourage taking first steps in that direct, and testing community-project fit validation before quite going full or near-full time!

Definitely. This was kicked off in the last month or two when there just seemed to be a bit more happening in OSS LLMs, but we are prioritizing diversifying this for the next cohort!

Love it!! Good luck with the mvps!

And thank you so much for the input - we are meeting the folks at ollama!!

Thank you so much for your work and enthusiasm here!! Unfortunately, that’s roughly the best way to approach it and how most of these have worked so far, demonstrations on smaller models (e.g. 7/13B), with slightly smaller datasets, catching the eye of the community, etc. in general it’s not a bad approach to research too, prove out concepts at smaller scale before scaling up!

Interesting, hadn’t thought of that, thank you! If you want to host end points Replicate is a great option, they also have a newer fine tuning api and solution! for raw VMs with GPUs right now it’s a bit situational and you have to try multiple different vendors tbh, also really depends on the capacity you need and which machines!!

Great callout @htrp... @appenz is our expert here btw !

We agree!!

thank you!! Indeed, we have been interacting in space very closely and doing our best to keep up and contribute where possible

Our pleasure :)

in most cases the teams already had their own source or platform of choice!

if the work is OSS/public and you aren't trying to start a VC-backed company, it could be! We usually want to see some early work already published, community reception and validation, but feel free to DM Matt or myself and we can take a look!

Hi HN, we are super excited to announce this new initiative!!

Please note, this program was designed to support individuals, teams, and hackers who are not pursuing commercial companies. Nevertheless, these projects push the state of the art in open source AI and help provide us with a more robust and comprehensive understanding of the technology as it is developed.

We are really proud to be contributing in this small fashion and grateful to the first cohort and all others contributing in this space!

amazing @simonw !!

the cog template is just starter code to make it super simple to deploy llama-v2 on any infrastructure of your choosing!

More about cog https://github.com/replicate/cog

Our thinking was just that a bunch of folks will want to fine-tune right away, then deploy the fine-tunes, so trying to make that easy... Or even just deploy the models-as-is on their own infra without dealing with CUDA insanity!

This is an emerging space with lots of interesting tools coming out... There are many established benchmarks out there (i.e. included on front page of llama2 release), but most product builders have their own sets of evals that are more relevant to them...

Here is a thread exploring differences between llama-v2 vs. gpt3.5: https://twitter.com/rajko_rad/status/1681344850510376960

We were trying to do the same thing once deployed haha... we found, if you want it to take on another persona, you could end your prompt as:

'Assistant: (responding as XYZXYZ)'

And then let it complete! Worked much more reliably than just saying: 'XYZXYZ:'

Hey HN, we've released tools that make it easy to test LLaMa 2 and add it to your own app!

Model playground here: https://llama2.ai

Hosted chat API here: https://replicate.com/a16z-infra/llama13b-v2-chat

If you want to just play with the model, llama2.ai is a very easy way to do it. So far, we’ve found the performance is similar to GPT-3.5 with far fewer parameters, especially for creative tasks and interactions.

Developers can:

* clone the chatbot app as a starting point (https://github.com/a16z-infra/llama2-chatbot)

* use the Replicate endpoint directly (https://replicate.com/a16z-infra/llama13b-v2-chat)

* or even deploy your own LLaMA v2 fine tune with Cog (https://github.com/a16z-infra/cog-llama-template)

Please let us know what you use this for or if you have feedback! And thanks to all contributors to this model, Meta, Replicate, the Open Source community!

Hi @swyx, Thanks for the kind words!

we actually just purposefully left that part a bit scarce because we have something else coming up on the topic! I'm sure we will be chatting through it soon :)

This is an excellent list of additions! We will try to include it shortly!

I left my AirPods case in my seat, realized walking toward baggage area, wouldn’t let me go back to get them.. assured me someone would go get them for me… I filed a claim, they said they couldn’t find them there… now I see my AirPods case in an apartment complex in the Bronx… nothing I can do….