HackerTrans
TopNewTrendsCommentsPastAskShowJobs

dnnssl2

no profile record

Submissions

MirageLSD: The First Live-Stream Video Diffusion Model (∞-Generation, 0-Latency)

mirage.decart.ai
9 points·by dnnssl2·hace 12 meses·9 comments

Oasis: A Universe in a Transformer (Playable Demo)

oasis.decart.ai
8 points·by dnnssl2·hace 2 años·1 comments

Anyscale Appoints Keerti Melkote as CEO

anyscale.com
2 points·by dnnssl2·hace 2 años·0 comments

Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models [pdf]

publications.reka.ai
2 points·by dnnssl2·hace 2 años·0 comments

comments

dnnssl2
·hace 2 meses·discuss
70% at launch seems pretty saturated, why ship a benchmark frontier models are about to top out on?
dnnssl2
·hace 12 meses·discuss
MirageLSD: The First Live-Stream Diffusion (LSD) Model - A Vid2Vid running in real time, infinite generation, zero latency. Available now in a live-hosted unlimited demo at https://mirage.decart.ai!

Please check out our Wired article on this model: https://www.wired.com/story/decart-artificial-intelligence-m...
dnnssl2
·el año pasado·discuss
What can this handle? Code? Browser? Computer Use?
dnnssl2
·hace 2 años·discuss
Oasis is playable so therefore:

1. Non-cherrypicked in its consistency (if you look at the demonstrations in the Oasis blog post you can find specific cases of consistency which is an anomaly rather than the norm)

2. Is live-inferenced at 20fps. If you use Runway v3 which is a comparably larger and higher quality model (resolution and consistency) it might take a minute or two generate 10 seconds of video.

3. Is served (relatively) reliably at consumer scale (with queues of 5-10k concurrent players) which means that in order to save on GPU cost, you increase batch size and decrease model size to “fit” more players in 1 GPU.
dnnssl2
·hace 2 años·discuss
Blog Post: https://oasis-model.github.io/

Model Weights: https://huggingface.co/Etched/oasis-500m
dnnssl2
·hace 2 años·discuss
What is the upper bound on the level of improvement (high performance networking, memory and compute) you can achieve with ternary weights?
dnnssl2
·hace 2 años·discuss
What’s the difference between all of the other query optimization startups? Bluesky, etc.
dnnssl2
·hace 3 años·discuss
How does one select a good candidate for the draft model in speculative decoding? I imagine that there's some better intuition than just selecting the next parameter count down (i.e 70B -> 13B, 13B -> 7B).

Also how does that interact with MoE models? Do you have a mini version of the MoE, with smaller experts?
dnnssl2
·hace 3 años·discuss
Is this still the case for sliding window attention/streaming LLMs, where you have a fixed length attention window rather than infinitely passing in new tokens for quadratic scaling? You even get better performance due to purposely downsampling non-meaningful attention sink tokens.
dnnssl2
·hace 3 años·discuss
That's not so much a use case, but I get what you're saying. It's nice that you can find optimizations to shift down the pareto frontier of across the cost and latency dimension. The hard tradeoffs are for cases like inference batching where it's cheaper and higher throughput but slower for the end consumer.

What's a good use case for an order of magnitude decrease in price per token? Web scale "analysis" or cleaning of unstructured data?
dnnssl2
·hace 3 años·discuss
If you were to serve this on a datacenter server, is the client to server roundtrip networking the slowest part of the inference? Curious if it would be faster to run this cloud GPUs on better hardware but farther compute, or locally with worse hardware.
dnnssl2
·hace 3 años·discuss
What are some of the better use cases of fast inference? From my experience using ChatGPT, I don't need it to generate faster than I can read, but waiting for code generation is painful because I'm waiting for the whole code block to format correctly, be available to copy or execute (in the case of code interpreter). Anything else fall under this pattern?
dnnssl2
·hace 3 años·discuss
Under the same conditions where enterprise versions of the API have significantly less latency and better reliability than personal. OpenAI can change anything about the underlying infrastructure.
dnnssl2
·hace 3 años·discuss
There are a few reputable academic examples of factual editing, such as: https://rome.baulab.info/

I don’t believe that the answer is strictly no. There are still many questions around the fine tuning method and the scale of data, as well as expectations of task accuracy from the perspective of an end user.
dnnssl2
·hace 3 años·discuss
Knowledge instillation is probably the holy grail of fine tuning. The hard part is:

1. Generalizing new facts. You can create a question answer pair of: “what is the population of the world in 2023?” “8 billion”, but it may not be able to pick up alternate phrasing or “does the world have 8 billion people on it?”

2. Catastrophic and behavioral forgetting. Continued fine tuning after RLHF and instruction fine tuning may result in the loss of the alignment and instruction following capabilities trained by OpenAI. At worst, it will start spewing random tokens like the example in the post.

I have not yet seen it successfully done, and I suspect that updating fractions (~.1%) of the original weights with PEFT methods won’t help.