Giter VIP home page Giter VIP logo

Comments (2)

ryanspice avatar ryanspice commented on June 26, 2024

+1 to this, after crawling 5000+ pages sad to have it fail!

from gpt-crawler.

MrAshRhodes avatar MrAshRhodes commented on June 26, 2024

@ryanspice
I think I've got a workaround.

I made changes to the following files GptEncoding.js and specialTokens.jsin node_modules\gpt-tokenizer\esm\

Change the following function in GptEncoding.js

    encodeGenerator(lineToEncode, { allowedSpecial = new Set(), disallowedSpecial = new Set(), } = {}) {
        // Assuming ALL_SPECIAL_TOKENS is a placeholder for all special tokens
        if (disallowedSpecial.has(ALL_SPECIAL_TOKENS)) {
            disallowedSpecial = new Set(this.specialTokenMapping.keys());
            allowedSpecial.forEach(token => disallowedSpecial.delete(token));
        }
        
        // Check for disallowed tokens in the input
        disallowedSpecial.forEach(token => {
            if (lineToEncode.includes(token)) {
                throw new Error(`Disallowed special token found: ${token}`);
            }
        });
    
        return this.bytePairEncodingCoreProcessor.encodeNative(lineToEncode, allowedSpecial);
    }

Then in specialTokens.js replace these bits.

export const EndOfText = "<EOT>";
export const FimPrefix = "<FimPrefix>";
export const FimMiddle = "<FimMiddle>";
export const FimSuffix = "<FimSuffix>";
export const ImStart = "<ImStart>";
export const ImEnd = "<ImEnd>";
export const ImSep = "<ImSep>";
export const EndOfPrompt = "<EndOfPrompt>";

from gpt-crawler.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.