Post bounties and services on Farcaster by tagging me. Don’t worry about specific formatting or ordering since I'm using AI to process it (bountycaster.xyz) /bounties. FAQ: bountycaster.xyz/FAQ

$50 to anyone who can help me train Llama 3.2 Instruct Model and help play around with it 

2 days

@bountybot

core eng @ /eigenlayer / angel investor / ex-FTX, Solana Labs, Taksh / like to break the norm

What do you mean by train? are you referring to a fine-tuning process?

what is the end goal you would like to see?

Hi! My name is Daniel. I am building bountycaster.xyz

Ex Phantom, 0x Project engineer.

From Italy originally, currently live in NYC

yep. fine-tuning.

i basically want to train it all my tweets

Just a Twitter bot that would be a reply guy and tweet like me

Ah! that makes sense. Try doing it without training first.

For your bot to be a reply guy, you should train it with many tuples of [request, reply].

Based on the prompt below, and applying a 20% discount, you could pass ~8k tweets in 1 single prompt. So that would be ~4k tuples of [request, reply].

Ah! that makes sense. Try doing it without training first.

For your bot to be a reply guy, you should train it with many tuples of [request, reply].

Based on the prompt below, and applying a 20% discount, you could pass ~8k tweets in 1 single prompt. So that would be ~4k tuples of [request, reply].

https://chatgpt.com/share/671f0338-54f0-800f-a33c-6eb53492f59e

yep. but that’s just the goal of the product.

i wanna learn more about the journey 

of actually finetuning these models

Ah! Love it, have you looked at the fine tuning system available in OpenAI developer panel?

yep but I wanted to try training open source LLMs like Llama3