metadata

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

      ### Response:
  - text: |-
      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
Dataset: KnutJaegersberg/WizardLM_evol_instruct_V2_196k_instruct_format
Training parameters: training_params.json

Prompt format

It was trained in the following prompt format:

### Instruction:
<instruction>

### Response: