README.md

---
license: apache-2.0
tags:
- autotrain
- text-generation
base_model: Locutusque/TinyMistral-248M
datasets:
- tatsu-lab/alpaca
widget:
- text: |-
    Find me a list of some nice places to visit around the world.
    
    ### Response:
- text: |-
    Tell me a story.
    Once upon a time...
    
    ### Response:
inference:
  parameters:
    max_new_tokens: 32
    repetition_penalty: 1.15
    do_sample: true
    temperature: 0.5
    top_p: 0.5
---

# Locutusque's TinyMistral-248M trained on the Alpaca dataset using AutoTrain

- Base model: [Locutusque/TinyMistral-248M](https://huggingface.co/Locutusque/TinyMistral-248M)
- Dataset: [tatsu-lab/alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca)
- Training: 2h under [these parameters](https://huggingface.co/Felladrin/TinyMistral-248M-Alpaca/blob/93533a5f190f79a8ad5e5a9765ce9ec498dfa5bd/training_params.json)
- Availability in other ML formats:
  - GGUF: [afrideva/TinyMistral-248M-Alpaca-GGUF](https://huggingface.co/afrideva/TinyMistral-248M-Alpaca-GGUF)
  - ONNX: [Felladrin/onnx-int8-TinyMistral-248M-Alpaca](https://huggingface.co/Felladrin/onnx-int8-TinyMistral-248M-Alpaca)

## Recommended Prompt Format

```
<instruction>

### Response:
```

## Recommended Inference Parameters

```yml
repetition_penalty: 1.15
do_sample: true
temperature: 0.5
top_p: 0.5
```