Switched safetensor base back to swe-dk-finetune-step-1000 (SOTA model)

Replaced EOT with end of text in accordance with LLM2Vec

Changed EOS token to end_of_text to follow LLM2Vec

Updated padding side to "left"

Model save

Training in progress, step 3000

Training in progress, step 2500

Training in progress, step 2000

Training in progress, step 1500

Training in progress, step 1000

Training in progress, step 500

Model save

Training in progress, step 4

Training in progress, step 2

Updated EOS token to left padding and <end_of_text>

tokenizer config from llama-swe last training

Added custom config in line with llm2vec

Add adapter config and model to main branch

initial commit