---
library_name: peft
tags:
- text-generation
license: apache-2.0
metrics:
- loss
language:
- en
---
## QLoRA weights using Llama-2-7b for the Code Alpaca Dataset

This model was fine-tuned using [Predibase](https://predibase.com/), the first low-code AI platform for engineers.
I fine-tuned base Llama-2-7b using LoRA with 4 bit quantization on a single T4 GPU.

Dataset: https://github.com/sahil280114/codealpaca

To use these weights:
```python
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM

config = PeftConfig.from_pretrained("arnavgrg/codealpaca-qlora")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
model = PeftModel.from_pretrained(model, "arnavgrg/codealpaca-qlora")
```

Prompt Template:
```
Below is an instruction that describes a task, paired with an input
that provides further context. Write a response that appropriately
completes the request.

### Instruction: {instruction}

### Input: {input}

### Response:
```

## Training procedure

The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16

### Framework versions


- PEFT 0.4.0