On the other side of the equation I've been spending much more time on code-review on an open source project I maintain, because developers are much more productive and I still code-review at the same speed. The real…
Is there a public curated list of "good ips" to whitelist ?
imho that is just silly ... I can see various ways censorship and freedom and common good at the same time. Actually, I can imagine different set ups where this could work... But then, you have to define these things.…
Of course one can generalize using the colloquial "Here in Europe". And generalization is useful -- one cannot go into all the complexity and details all the time, at some point one has to summarize/generalize an…
Just for another data point, I took me 4 days to cook up a WASM front-end using Go for my otherwise command-line only Hive game: https://janpfeifer.github.io/hiveGo/www/hive/ Probably everything JS and DOM is better…
I think there is a misconception there. Go is as good a language as any for an ML framework. Better if you buy into it being better for its simplicity. It's clearly a worse if you factor in the ecosystem that already…
A few considerations come to mind: 1. The O(N^2*d) computation cost of the attention layers. For large graphs (millions of nodes) it's quickly too costly. And in some of the social network problems, the more data you…
Thanks for the reply, but when you mean "fine-tuning" for the prompt, do you mean fine-tuning of the LLM encoder of the prompt right ? (The thing that transforms the prompt into a sequence of embeddings?) But that is…
Noob question: when folks talk about fine-tuning LLM, do they usually fine-tune the encoder (of the prompt), the decoder (that generates the text) or both ?
Sadly (but correctly) nothing is public, no one ever sees any data, it's a service. Pure FNN (feedforward NN) models, if I recall correctly is also ~30 to 40%. Since the server doesn't work for all types of data, and…
One way is to use categorical set splits [1] (proposed for categorical set inputs, but works for categorical features as well), used in TF-DF [1]. Greedy, and expensive to train (cheap inference though), but it gives…
I can't explain it, but I help maintain TensorFlow Decision Forests [1] and Yggdrasil Decision Forests [2], and in an AutoML system at work that trains models on lots of various users data, decision forest models gets…
DeepL translation "fork away" -> "Weggabelung" ... not much better :\",
On the other side of the equation I've been spending much more time on code-review on an open source project I maintain, because developers are much more productive and I still code-review at the same speed. The real…
Is there a public curated list of "good ips" to whitelist ?
imho that is just silly ... I can see various ways censorship and freedom and common good at the same time. Actually, I can imagine different set ups where this could work... But then, you have to define these things.…
Of course one can generalize using the colloquial "Here in Europe". And generalization is useful -- one cannot go into all the complexity and details all the time, at some point one has to summarize/generalize an…
Just for another data point, I took me 4 days to cook up a WASM front-end using Go for my otherwise command-line only Hive game: https://janpfeifer.github.io/hiveGo/www/hive/ Probably everything JS and DOM is better…
I think there is a misconception there. Go is as good a language as any for an ML framework. Better if you buy into it being better for its simplicity. It's clearly a worse if you factor in the ecosystem that already…
A few considerations come to mind: 1. The O(N^2*d) computation cost of the attention layers. For large graphs (millions of nodes) it's quickly too costly. And in some of the social network problems, the more data you…
Thanks for the reply, but when you mean "fine-tuning" for the prompt, do you mean fine-tuning of the LLM encoder of the prompt right ? (The thing that transforms the prompt into a sequence of embeddings?) But that is…
Noob question: when folks talk about fine-tuning LLM, do they usually fine-tune the encoder (of the prompt), the decoder (that generates the text) or both ?
Sadly (but correctly) nothing is public, no one ever sees any data, it's a service. Pure FNN (feedforward NN) models, if I recall correctly is also ~30 to 40%. Since the server doesn't work for all types of data, and…
One way is to use categorical set splits [1] (proposed for categorical set inputs, but works for categorical features as well), used in TF-DF [1]. Greedy, and expensive to train (cheap inference though), but it gives…
I can't explain it, but I help maintain TensorFlow Decision Forests [1] and Yggdrasil Decision Forests [2], and in an AutoML system at work that trains models on lots of various users data, decision forest models gets…
DeepL translation "fork away" -> "Weggabelung" ... not much better :\",