Do check out my other videos of building the RAG app using Ollama. Ollama RAG using LlamaIndex -> ua-cam.com/video/woBiq3Opg-Q/v-deo.html Ollama RAG -> ua-cam.com/video/et_EREAsIQE/v-deo.html Learn Ollama -> ua-cam.com/video/vfm_Pmxe-z8/v-deo.html
Hi, how can we train an LLM, say codelama, with our github repository or local repo, so that we can use the model to write new code following the code structure of the provided codebase?
You can take any existing model like CodeLlama and the fine-tune it on your codebase. It'll require GPU and the process will take time as well. You can use huggingface library for fine-tuning model. I'll create videos on fine-tuning LLMs in future.
Do check out my other videos of building the RAG app using Ollama.
Ollama RAG using LlamaIndex -> ua-cam.com/video/woBiq3Opg-Q/v-deo.html
Ollama RAG -> ua-cam.com/video/et_EREAsIQE/v-deo.html
Learn Ollama -> ua-cam.com/video/vfm_Pmxe-z8/v-deo.html
Great video, thanks!
Thanks for taking time to comment. Really appreciate it.
Good video. Thanks for sharing..
Thanks for watching!
Hi, how can we train an LLM, say codelama, with our github repository or local repo, so that we can use the model to write new code following the code structure of the provided codebase?
You can take any existing model like CodeLlama and the fine-tune it on your codebase. It'll require GPU and the process will take time as well. You can use huggingface library for fine-tuning model. I'll create videos on fine-tuning LLMs in future.
❤❤
Thanks for your support.