PULI LlumiX 32K instruct (6.74B billion parameter)
Intruct finetuned version of NYTK/PULI-LlumiX-32K.
Training platform
Lightning AI Studio L4 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
In total ~30k instructions were selected.
Prompt template: ChatML
<|im_start|>system
Az alábbiakban egy feladatot leíró utasítás található. Írjál olyan választ, amely megfelelően teljesíti a kérést.<|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
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