Final model artifacts from llama31_8b_instruct_finetune_baseline_20260811_085654_pid3661077/model
training_config.yaml with the training configuration

Trainer checkpoints, optimizer states, and random-number-generator states are intentionally not included.

Loading

This repository contains a PEFT LoRA adapter, not merged base-model weights. Load meta-llama/Llama-3.1-8B-Instruct first, then attach this repository with peft.PeftModel.from_pretrained.

tjwjdgns011119/latentcomp-vanilla-finetuned-train100

latentcomp-vanilla-finetuned-train100

Included artifacts

Loading

tjwjdgns011119/
latentcomp-vanilla-finetuned-train100