I've just been using SillyTavern for the Gemini API.Can you teach me how to configure the api for use in this tool or can you share the configurations? thanks
nice find lmaothe API is still censored, but the filter seems less restricted for the newest 4 Turbo model from my testing, anyways.
By the way, google's newest model, the Gemini pro 1.5 is really cool. Super fast, free and honestly, pretty funny to cheat its restrictions. I found out, if you just give it lines as if they were HTML, it'll be more likely to translate lewd Japanese.
Here's something I translated using it. It's just a novel using HTML, but it's really good if you like forced transformation, feminization, bestiality, femdom and forced MtF surgery. I'll probably upload it in its own thread later when I go through it and clean it up.
this 8k context can take how many chars (in and out)?I tried it, but nothing worked. Maybe it's just a skill issue for me :L
Been using it on Groq and for only being a 70b model, it does things only 100+b models could do months ago. It's actually really crazy. Sadly it only has 8k context, which means anything besides double checking a few phrases makes it pointless.
Though, I did a quick experiment.
Using the same system prompt I did a
Translation for:
「まさか勇者様、冗談なのです? あんな雑魚なんかこれからいくらでも戦うことになるのです。さっさと本気で消し去るのです」
Command R Plus:
“You can’t be serious, Your Highness the Hero. We’re going to be fighting that kind of weakling from now on. Get serious and wipe them out.”
GPT4 Turbo (Don't know why it kept Yuusha, which can mean brave and or Hero, untranslated?):
"Could it be, Yuusha-sama, that this is a joke? We'll be fighting plenty such small fries from now on. Just seriously wipe them out quickly."
And Llama 3:
"What, you're the brave hero, joking around? Those small fries will be a piece of cake to defeat from now on. Let's get serious and crush them already."
Now, looking at Llama3, it's still stilted compared to the other two much bigger and stronger models, but look what happens when I ask each to explain it
GPT4 explanation:
View attachment 3563254
Command R Plus explanation:
View attachment 3563256
Notice how those two didn't really explain much? Command R is close, but still doesn't really explain the whole thing.
Now look at what Llama3 does:
View attachment 3563262
Despite each using the same system prompt and given the same amount of context, Llama3, even though it gave a much more stilted translation, gives not just explanations, but a step by step guide of how it got the translation it did. And again, this is a much smaller model even compared to Command R plus. It makes me hopeful for the 400+b model Mark Zuckerberg mentioned META still had training (Hopefully with more context) Because at this rate, Mark Zuckerberg might actually be the unironic winner of the text generation AI race.
Honestly couldn't tell you, i'm not that smart.this 8k context can take how many chars (in and out)?
yep was wondering the same thing since I tried making a tool myself to translate a game. I think dazed is replacing meanie words (cause text porn is such a big deal) using a dictionary so those aren't sent to the AI. if this is indeed the techinique used, I don't understand how the translated phrases, with in some cases half content missing (your //// is so huge onii-chan), turn out making sense though.I'm wondering how this bypasses Chat GPT's filters? When I mention even slightly sexual content to those chat bots, they usually start losing their shit. Does the GPT API not have any such restrictions?
Nope. I don't replace anything the API just doesn't complain at me. No idea why.yep was wondering the same thing since I tried making a tool myself to translate a game. I think dazed is replacing meanie words (cause text porn is such a big deal) using a dictionary so those aren't sent to the AI. if this is indeed the techinique used, I don't understand how the translated phrases, with in some cases half content missing (your //// is so huge onii-chan), turn out making sense though.
Not sure I understand. The estimate is based on dollars and is calculated by going through the files and counting all the tokens using OpenAI's tokenizer. I have to guess what the output is going to be so its not 100% accurate, but generally the estimate is always around 20% higher than what the actual cost will be.What units, exactly, do the pricing variable come in?You must be registered to see the linksthe OpenAI site lists their pricing in dollars per million tokens. What figure does the pricing variable represent? They are pretty out of date, as OpenAI has significantly reduced their prices in the last two years.
GreatView attachment 2535664
You must be registered to see the links
You don't have permission to view the spoiler content. Log in or register now.You don't have permission to view the spoiler content. Log in or register now.You don't have permission to view the spoiler content. Log in or register now.
Switching to GPT4 -> https://f95zone.to/threads/dazedmtl...anslations-using-chatgpt.155635/post-11179712
Contributions:
OrcboIg - Implemented a better method for injecting past translated text for context. Improving translations overall.
List: elem0,elem1,elem2I'm trying to translate a cvs file and I get this error:
You don't have permission to view the spoiler content. Log in or register now.
Can someone help me?
CSV module only works with certain formats. You will have to edit the script if you want to adapt to your own specific script. A T++ export should work.I'm trying to translate a cvs file and I get this error:
You don't have permission to view the spoiler content. Log in or register now.
Can someone help me?
Im using a T++ export.CSV module only works with certain formats. You will have to edit the script if you want to adapt to your own specific script. A T++ export should work.
Send me your csv real quick.Im using a T++ export.
I added a value to the second column and that error is gone, but then I get this one:
You don't have permission to view the spoiler content. Log in or register now.
It's okay, I figured it out.Send me your csv real quick.
If there isn't a way to designate the speaker like some colors or something then no. Alternative, you can add colors to certain names and it should pick it upThe game I'm trying to translate don't have the 'speaker_name'. Instead the speaker name appears together with the dialogue, and when the tool translates it goes all in one line. There's a way to fix that with the prompt or with the code itself?
I do that in the original file or in the translated one?If there isn't a way to designate the speaker like some colors or something then no. Alternative, you can add colors to certain names and it should pick it up
"//C[4]Tom//C[0]" for example.
The original.I do that in the original file or in the translated one?