---
license: llama2
---

<h1>Kaori-34B-v1  Model Card</h1>

This Model was Finetuned By Kaeri and Jenti.

<h3>Datasets Strategy</h3>

 - Open-Platypus
 - Dolphin

We trained the model with 100% Open-Platypus data and 5% Dolphin data and applied SFT strategy.

We did not use GSM8k samples when generating data. 
Also we were careful of data contamination by similarity filtering 
the training data if the data correspond to any of the following list.

<pre>
filtering_tasks = [
    'cot_gsm8k',
    'cot_gsm8k_ii',
    'drop:2.0.0',
    'winogrande:1.1.0'
    'task228_arc_answer_generation_easy',
    'ai2_arc/ARC-Challenge:1.0.0',
    'ai2_arc/ARC-Easy:1.0.0',
    'task229_arc_answer_generation_hard',
    'hellaswag:1.1.0', 
    'task1389_hellaswag_completion'
]
</pre>


<h3>Framework:</h3>

 - https://github.com/hiyouga/LLaMA-Factory


<h3>Parameters:</h3>

 - Finetune_Type  :	 LoRA
 - GPUs           :  A100x4(80GB)
 - Epochs         :  3
 - Batchsize      :  8