- 6 Posts
- 21 Comments
herozorro@alien.topBto
LocalLLaMA•Tool to quickly iterate when fine-tuning open-source LLMsEnglish
1·3 years agocould you provide some directions on how to fine tune the model for coding? i have a ui framework in python that i would like to feed it the docs and some github repos code.
how would the dataset look like for that? should i be formulating different uses cases on the framework as if the user is asking?
in addition, do i need to provide standard python code or do those base modles have code in them already?
herozorro@alien.topBto
LocalLLaMA•Are there any data cleaning focused LLMs? [also, rant]English
1·3 years agomost all of what you wrote can be done with python out of the box
Remember when you finish for the day that if you don’t delete the pod (and any storage you created) your credit balance will reduce while you are sleeping. But at least it can’t go negative and send you a big bill like evil AWS.
do they charge per hour like a parking meter or only when the pod is used
herozorro@alien.topBto
LocalLLaMA•Colud LLaVa be finetuned to perform image to markdown or even image to html conversion?English
1·3 years agowhat you are looking for is OCR. then feed the LLM to the markdown
i think its a great accomplishment and should be commend. congrats OP if its your project
cause the majority suck very bad compared to chatgpt
how much does it cost to do these fine tunes on RunPod? How much compute time is used
Lik $1000+?
Given their recently published paper, they probably figured out a way to get GPT to learn their own reward function somehow.
you just need 2 GPTs talking with each other. the seconds acts as a critic and guides the first
herozorro@alien.topBto
LocalLLaMA•any open source LLM you want scaled to 200 gpus I will create a tutorial forEnglish
1·3 years agoi dont understand where is this supposed to run? at a cloud provider? so this script is instlaled there, and it handles the distribution?
i read the docs for the site and i must say these questions where not answered. perhaps a ‘what is burla’
herozorro@alien.topBto
LocalLLaMA•Is anyone else experiencing an unExpected anxiety feeling about the Altman news? Idk why, but I’m freaked out
1·3 years agoWhy? Are you a mega fan boy?
herozorro@alien.topBto
LocalLLaMA•OpenAI announces leadership transition: Sama no longer CEOEnglish
1·3 years agoThe irony now is that Grok will have the latest info on this as people are tweeting about it
herozorro@alien.topBto
LocalLLaMA•Sam Altman out as CEO of OpenAI. Mira Murati is the new CEO.
1·3 years agoRight after President Xi visit…
herozorro@alien.topBto
LocalLLaMA•Generalized Tree-of-Thought Capability in SynthIA ModelsEnglish
1·3 years agocan someone explain what is meant by this
Generate your dataset with this, plus the Orca system prompts.
how do you reboot it after the coolab dies
how long does it stay alive/online?
herozorro@alien.topBto
LocalLLaMA•We are Higgsfield AI. We have a large GPU cluster and want to finetune your dataset.English
1·3 years agobut what would be the proper formatting example for code? just paste in a bunch of files from a repo? or should be more a cheatsheet format?
herozorro@alien.topBto
LocalLLaMA•We are Higgsfield AI. We have a large GPU cluster and want to finetune your dataset.English
1·3 years agoplease do something like this, or provide detailed example, on how an open source framework api can be added to a coder LLM.
how do we prepare the data with code sample, docs, so the coder LLM learns it can can do code completions and answer documentation?
herozorro@alien.topBto
LocalLLaMA•RAG in a couple lines of code with txtai-wikipedia embeddings database + MistralEnglish
1·3 years agohow can this be used for code generation with a github repo and its documentation?
what is this script supposed to output?
will this speed up ollama project?