README.md

---
license: apache-2.0
tags:
  - autotrain
  - text-generation
base_model: Locutusque/TinyMistral-248M
datasets:
  - KnutJaegersberg/WizardLM_evol_instruct_V2_196k_instruct_format
widget:
  - text: |-
      ### Instruction:
      Which places do you recommend I visit around the world?

      ### Response:
  - text: |-
      ### Instruction:
      Write a story about some magical place.

      ### Response:
  - text: |-
      ### Instruction:
      Tell me all you know about the Earth.
      
      ### Response:
inference:
  parameters:
    max_new_tokens: 32
    repetition_penalty: 1.15
    do_sample: true
    temperature: 0.5
    top_p: 0.15
---

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

- Base model: [Locutusque/TinyMistral-248M](https://huggingface.co/Locutusque/TinyMistral-248M)
- Dataset: [KnutJaegersberg/WizardLM_evol_instruct_V2_196k_instruct_format](https://huggingface.co/datasets/KnutJaegersberg/WizardLM_evol_instruct_V2_196k_instruct_format)
- [Training hyperparameters](https://huggingface.co/Felladrin/TinyMistral-248M-Evol-Instruct/blob/85723f768c439307c996328d68fe7df2947237ae/training_params.json)
- Availability in other ML formats:
  - GGUF: [afrideva/TinyMistral-248M-Evol-Instruct-GGUF](https://huggingface.co/afrideva/TinyMistral-248M-Evol-Instruct-GGUF)

## Recommended Prompt Format

```
### Instruction:
<instruction>

### Response:
```