README.md

---
language: en
tags:
- llama-2
- lora
- ranking
license: apache-2.0
---

# bytestorm/SKIM-orcas-kdd25

This is a LoRA-tuned checkpoint of Llama-2-7b for ranking tasks.

## Model Details

- **Base Model:** Llama-2-7b
- **Training Type:** LoRA fine-tuning
- **Task:** Ranking/Retrieval
- **Framework:** PyTorch

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("bytestorm/SKIM-orcas-kdd25")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf")
```