Скачать с ютуб LLM Finetuning Part3: Saving and Deployment after Finetuning LLM with Unsloth, LoRA and SFTTrainer в хорошем качестве

LLM Finetuning Part3: Saving and Deployment after Finetuning LLM with Unsloth, LoRA and SFTTrainer

In this LLM Fine tuning project, saving, merging, pushing/deploying to hugging face hub, pulling of fine-tuned LLM from hugging face hub and evaluation are done step-by-step after fine tuning the LLM (Llama3.2) with our own QA (question-answer) type of data. Fine tuning of the model was done with Unsloth library using LoRA (Low-Rank Adaptation) technique. SFTTrainer (trl) etc. GitHub Link: https://github.com/dharsandip/fine_tu... LinkedIn:   / sandip-dhar-40145546   #finetuningllm, #huggingface, #unsloth, #llamafinetuning, #llmproject, #llmtutorial, #lora, #SFTTrainer, #python, #huggingfacehub, #llmfinetuning, #llmfinetuning, #finetunellm, #finetuning, #peftfinetuning, #llm Please watch LLM Finetuning Part1:    • Fine tuning DeepSeek-R1 LLM with cust...   Please watch LLM Finetuning Part2:    • Prepare Q&A data from scratch, Fine t...