PULI-LlumiX-32K-instruct-lora-0.2

PULI LlumiX 32K instruct (6.74B billion parameter)

Intruct finetuned version of NYTK/PULI-LlumiX-32K.

Training platform

Runpod RTX 4090 GPU

Hyper parameters

• Epoch: 3
• LoRA rank (r): 16
• LoRA alpha: 16
• Lr: 2e-4
• Lr scheduler: cosine
• Optimizer: adamw_8bit
• Weight decay: 0.01

Dataset

boapps/szurkemarha

Only Hungarian instructions were selected: ~53000 prompts.

Prompt template: ChatML

<|im_start|>system
Egy segítőkész mesterséges intelligencia asszisztens vagy. Válaszold meg a kérdést legjobb tudásod szerint!<|im_end|>
<|im_start|>user
Ki a legerősebb szuperhős?<|im_end|>
<|im_start|>assistant
A legerősebb szuperhős a Marvel univerzumában Hulk.<|im_end|>

Base model

• Trained with OpenChatKit github
• The LLaMA-2-7B-32K model were continuously pretrained on Hungarian dataset
• The model has been extended to a context length of 32K with position interpolation
• Checkpoint: 100 000 steps

Base model dataset for continued pretraining

• Hungarian: 7.9 billion words, documents (763K) that exceed 5000 words in length
• English: Long Context QA (2 billion words), BookSum (78 million words)

Limitations

• max_seq_length = 32 768
• float16
• vocab size: 32 000