TeeZee's picture
Update README.md
6ee7576 verified
---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
base_model: unsloth/llama-2-7b-bnb-4bit
---
After just 600 steps (80 minutes of training on free colab) effects are amazing:
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
explain what is machine learinig
### Response:
Machine learning be th' study of computer algorithms to mimic th' way humans learn and make decisions.
Machine learning uses data with known outcomes (called "labeled" data) to improve its performance on new, unseen data ("unlabeled" data).
Thar she blows! Blow me down!
```
# Uploaded model
- **Developed by:** TeeZee
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-2-7b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)