micheal65536

joined 1 year ago
[–] [email protected] 2 points 10 months ago

In that case ChatGPT is correct, it cannot work with links. You will need to download the video transcript (subtitles) yourself and ask it to summarise that. This definitely works, people have been doing it for months.

[–] [email protected] 2 points 11 months ago

Probably another case of "I don't want people training AI on my posts/images so I'm nuking my entire online existence".

[–] [email protected] 2 points 11 months ago

Without knowing anything about this model or what it was trained on or how it was trained, it's impossible to say exactly why it displays this behavior. But there is no "hidden layer" in llama.cpp that allows for "hardcoded"/"built-in" content.

It is absolutely possible for the model to "override pretty much anything in the system context". Consider any regular "censored" model, and how any attempt at adding system instructions to change/disable this behavior is mostly ignored. This model is probably doing much the same thing except with a "built-in story" rather than a message that says "As an AI assistant, I am not able to ...".

As I say, without knowing anything more about what model this is or what the training data looked like, it's impossible to say exactly why/how it has learned this behavior or even if it's intentional (this could just be a side-effect of the model being trained on a small selection of specific stories, or perhaps those stories were over-represented in the training data).

[–] [email protected] 5 points 1 year ago (1 children)

IMO, local LLMs lack the capabilities or depth of understanding to be useful for most practical tasks (e.g. writing code, automation, language analysis). This will heavily skew any local LLM "usage statistics" further towards RP/storytelling (a significant proportion of which will always be NSFW in nature).

[–] [email protected] 5 points 1 year ago

Stable Diffusion 2 base model is trained using what we would today refer to as a "censored" dataset. Stable Diffusion 1 dataset included NSFW images, the base model doesn't seem particularly biased towards or away from them and can be further trained in either direction as it has the foundational understanding of what those things are.

[–] [email protected] 2 points 1 year ago

You are correct, page 10 does say that the hook point should meet 1/8 inch above the needle eye, at the bottom of the needle's stroke.

Missing stitches only when the fabric is in place suggests that your thread tension may be too high. Check the top thread tension, make sure that you can pull the thread through with only a slight pull at the "0" position (check page 9 of the service manual).

[–] [email protected] 4 points 1 year ago (2 children)

This sounds like a timing issue to me. The thread bunching up may be due to the hook not grabbing the thread or the take-up lever not taking up the slack at the correct time. If it's missing stitches in zig-zag mode then that would also be due to either hook timing or possibly needle bar alignment.

Simple things to check:

  • Make sure that the needle is installed correctly, especially that it is oriented the right way and inserted all the way in

  • Make sure that the take-up lever is threaded correctly

Assuming these are both correct, you can try the following:

  • If possible, insert a fresh needle (at least, you will need a needle that is undamaged and not bent from the shank up to the eye)

  • Remove the plate, leave the machine unthreaded

  • On the straight stitch setting, turn the hand wheel slowly and check that the eye of the needle is exactly level with the hook as they pass each other (this should happen close to the bottom of the needle's stroke but may not be exactly at the bottom)

  • On the widest zig-zag stitch setting, again turn the hand wheel slowly and check that the eye of the needle passes closely to the hook (it won't be exact because the needle has moved, but it should be just slightly early on one side and just slightly late on the other, not noticeably early or late on one side) and also check that the needle is not colliding with any solid parts of the machine on either side

If the eye and the hook are not aligned as they pass each other, then you have either a timing or a needle height alignment issue. If they pass correctly on the straight stitch but the needle is noticeably early or late on one side of the zig-zag stitch (and fine on the other side) then you have an issue with the horizontal alignment of the zig-zag stitch.

[–] [email protected] 1 points 1 year ago

That machine is a pretty solid choice if it works, and a worthwhile repair project if it doesn't (it may have seized up if not maintained recently or it may have timing or alignment issues from age).

Machines like that are quite solidly built compared to modern machines, I would be surprised if it can't get through a few layers of denim for a few stitches (I wouldn't recommend doing 6 layers continuously, but crossing over the side seam should be OK). If you're concerned you can always hand crank it for that part.

The lack of a free arm may be somewhat limiting for hems. The "stupid" solution would be to stand the machine up on top of a crate or similar, as long as the circumference of the leg/other fabric is large enough to fit around the bottom metal "plate" of the machine. (These machines have a metal body designed to be built into a cabinet or shelf top. I'm not sure if yours includes a wooden box around the bottom or if it is just the machine itself, but if there is any wood then the machine can be removed from this leaving just the metal body of the machine itself which may provide more flexibility in this regard.)

[–] [email protected] 1 points 1 year ago (3 children)

I haven't come across any significant discussion surrounding this before and I wouldn't recommend choosing a machine on this basis.

A front-loading bobbin is only an advantage for changing mid-task if you catch it before the thread runs out, otherwise you'll be backtracking and starting again anyway once you've replaced it. I suppose if there is a viewing window and you can see when it is about to run out then this is an advantage, otherwise you won't know when to stop and change it anyway until you notice that it has already run out.

In terms of speed I doubt you will find any typical sewing machine "too slow" unless you plan to sew a lot and you want it finished quickly. For a few repairs or alterations and the occasional custom piece speed is not a priority, most of the time you will want to go slower anyway for more control/accuracy.

I think you need to put less thought into what machine you get and more thought into getting some machine and start sewing without thinking so much about details like how the bobbin is loaded. As a beginner these things don't matter, and by the time you are non-beginner enough for them to matter then you will know what aspects are important to you and if you want to upgrade. As it is, you can't really jump to making "expert-level" choices because you don't have the experience to know, for example, if speed is even a priority to you.

[–] [email protected] 1 points 1 year ago (1 children)

There doesn't appear to be a model anywhere, unless that has been published completely separately and not mentioned anywhere in the code documentation.

[–] [email protected] 2 points 1 year ago (4 children)

So... If this doesn't actually increase the context window or otherwise increase the amount of text that the LLM is actually able to see/process, then how is it fundamentally different to just "manually" truncating the input to fit in the context size like everyone's already been doing?

[–] [email protected] 2 points 1 year ago

Singer are by far the best for finding replacement parts and repair guides, followed somewhat by Brother. I would recommend avoiding the others if you want to be able to maintain or repair the machine in the future.

The stitch patterns should be documented in the manual. Otherwise they are somewhat self explanatory. The symbol looks somewhat like how the stitch will look. Straight stitch is usually a straight line (possibly dashed or dotted), and is usually the first pattern listed. Zigzag stitch looks like a line that moves from side to side in evenly-spaced triangles and is usually the second pattern.

There may also be various asymmetrical variations of the zigzag stitch, or ones that get narrower and wider over time, these are probably what you're referring to as "all the other symbols". Most of these will function as stretch stitches but you don't need to use or care about them unless you specifically want them for their appearance. They make no functional difference. Some of the more elaborate ones may not stretch evenly or adequately.

If the machine has a straight stretch stitch option (as I explained in my other comment) then the symbol for this may vary so check the manual. It's usually some sort of a straight line with dots or dashes.

Some machines also have a button hole mode which is usually listed alongside the other stitch options. Again the symbol for this can vary but it is usually some sort of a rectangle with wavy lines, and it is usually clearly marked in a different color or with a border around it or similar to distinguish it from the others.

Regarding needles, spools, etc.: Needles are completely standard and replaceable and interchangeable on all machines except antiques and this should be the first thing that you do anyway. You can get a twin needle for specific tasks but generally you won't need one, it is not "more useful" than having just a single needle (this is not a "two is better than one" situation). The most important thing to make sure that you have is the presser foot, there should be one attached to the machine and most machines are intended to include one or two other types that can be swapped out (e.g. a narrower one that is useful for particular types of fabric or for working in tight situations) and if these are missing then you will have to try to find replacements or do without as they are mostly NOT interchangeable between machines of different brands or families. Check the manual for what accessories should be included, and make sure to look for them in the accessories compartment. It would be useful if the machine included one or two bobbins so that you can get started sooner but these are mostly standard and easy to find online (there are a few different types so make sure you work out what type you need).

I would highly recommend watching a few beginner/introductory machine sewing tutorials so that you can learn about the various parts of the machine and how it is set up and used, even if you aren't planning on doing any actual sewing from scratch. This will make it a lot easier to know what you need and understand what you're looking at.

 

You are probably familiar with the long list of various benchmarks that new models are tested on and compared against. These benchmarks are supposedly designed to assess the model's ability to perform in various aspects of language understanding, logical reasoning, information recall, and so on.

However, while I understand the need for an objective and scientific measurement scale, I have long felt that these benchmarks are not particularly representative of the actual experience of using the models. For example, people will claim that a model performs at "some percentage of GPT-3" and yet not one of these models has ever been able to produce correctly-functioning code for any non-trivial task or follow a line of argument/reasoning. Talking to GPT-3 I have felt that the model has an actual in-depth understanding of the text, question, or argument, whereas other models that I have tried always feel as though they have only a superficial/surface-level understanding regardless of what the benchmarks claim.

My most recent frustration, and the one that prompted this post, is regarding the newly-released OpenOrca preview 2 model. The benchmark numbers claim that it performs better than other 13B models at the time of writing, supposedly outperforms Microsoft's own published benchmark results for their yet-unreleased model, and scores an "average" result of 74.0% against GPT-3's 75.7% while the LLaMa model that I was using previously apparently scores merely 63%.

I've used GPT-3 (text-davinci-003), and this model does not "come within comparison" of it. Even giving it as much of a fair chance as I can, giving it plenty of leeway and benefit of the doubt, not only can it still not write correct code (or even valid code in a lot of cases) but it is significantly worse at it than LLaMa 13B (which is also pretty bad). This model does not understand basic reasoning and fails at basic reasoning tasks. It will write a long step-by-step explanation of what it claims that it will do, but the answer itself contradicts the provided steps or the steps themselves are wrong/illogical. The model has only learnt to produce "step by step reasoning" as an output format, and has a worse understanding of what that actually means than any other model does when asked to "explain your reasoning" (at least, for other models that I have tried, asking them to explain their reasoning produces at least a marginal improvement in coherence).

There is something wrong with these benchmarks. They do not relate to real-world performance. They do not appear to be measuring a model's ability to actually understand the prompt/task, but possibly only measuring its ability to provide an output that "looks correct" according to some format. These benchmarks are not a reliable way to compare model performance and as long as we keep using them we will keep producing models that score higher on benchmarks and claim to perform "almost as good as GPT-3" but yet fail spectacularly in any task/prompt that I can think of to throw at them.

(I keep using coding as an example however I have also tried other tasks besides code as I realise that code is possibly a particularly challenging task due to requirements like needing exact syntax. My interpretation of the various models' level of understanding is based on experience across a variety of tasks.)

view more: next ›