|
--- |
|
tags: |
|
- autotrain |
|
- text-generation |
|
base_model: ahxt/llama2_xs_460M_experimental |
|
datasets: |
|
- KnutJaegersberg/WizardLM_evol_instruct_V2_196k_instruct_format |
|
widget: |
|
- text: "Once upon a time," |
|
--- |
|
|
|
# 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 parameters: [training_params.json](https://huggingface.co/Felladrin/llama2_xs_460M_experimental_evol_instruct/blob/cc151c5669ea37c3ef972e375c74f2d9bfd92b49/training_params.json) |
|
|
|
Note: Only the Lora Adapter for now. Merged base model is on the way. |
