README.md

---
inference: false
language:
- en
pipeline_tag: text-generation
tags:
- llama
- llama-2
license: mit
---

# llama-2-supercot-lora

Standard 8bit lora trained using [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) on the [supercot](https://huggingface.co/datasets/kaiokendev/SuperCOT-dataset) dataset using Alpaca instruct format at 4096 context:

```
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:
<any additional context. Remove this if it's not neccesary>

### Response:
<make sure to leave a single new-line here for optimal results>
```

## Bias, Risks, and Limitations
The model will show biases similar to those exhibited by the base model. It is not intended for supplying factual information or advice in any form.