README.md

---
tags:
- autotrain
- text-generation
base_model: ahxt/llama2_xs_460M_experimental
datasets:
- KnutJaegersberg/WizardLM_evol_instruct_V2_196k_instruct_format
widget:
- text: |-
    ### Instruction:
    Find me a list of some nice places to visit around the world.
    
    ### 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_k: 5
    top_p: 0.9
---

# ahxt's llama2_xs_460M_experimental trained on the WizardLM's Evol Instruct dataset using AutoTrain

- Base model: [ahxt/llama2_xs_460M_experimental](https://huggingface.co/ahxt/llama2_xs_460M_experimental)
- Dataset: [KnutJaegersberg/WizardLM_evol_instruct_V2_196k_instruct_format](https://huggingface.co/datasets/KnutJaegersberg/WizardLM_evol_instruct_V2_196k_instruct_format)
- Training: 13.5h under [these parameters](https://huggingface.co/Felladrin/llama2_xs_460M_experimental_evol_instruct/blob/cc151c5669ea37c3ef972e375c74f2d9bfd92b49/training_params.json)

## Prompt format

It was trained in the following prompt format:

```
### Instruction:
<instruction>

### Response:
```