coreset-selection/wpu_mod_20

1# wpu_mod_202 3> LoRA adapter uploaded automatically.4 5## Overview6- **Type:** LoRA adapter (PEFT)7- **Task type:** `CAUSAL_LM`8- **Base model:** `/home/praveen/coreset/outputs/llama_3_1_8b_finetuned`9- **LoRA r:** `8`10- **LoRA alpha:** `16`11 12## Usage13```python14from peft import PeftModel, PeftConfig15from transformers import AutoModelForCausalLM, AutoTokenizer16 17peft_model_id = "coreset-selection/wpu_mod_20"18cfg = PeftConfig.from_pretrained(peft_model_id)19base = cfg.base_model_name_or_path20tok = AutoTokenizer.from_pretrained(base)21model = AutoModelForCausalLM.from_pretrained(base, torch_dtype='auto')22model = PeftModel.from_pretrained(model, peft_model_id)23```24 25## Files26- `adapter_config.json`27- `adapter_model.bin` or `adapter_model.safetensors`28 29## Notes30- This repo contains only the LoRA adapter weights.31- Load with the matching base model specified above.32 33_Uploaded from: `/home/praveen/coreset/outputs/gd_mod_20_model`_