This is the fully trained version (with fixed formatting!!).

Dataset used: Gryphe/Sonnet3.5-SlimOrcaDedupCleaned which was further filtered to remove prompts/examples that are longer than 4076 tokens (removed about 385 examples).

Prompt format is: ChatML

LoRA: mpasila/Viking-SlimSonnet-v1-LoRA-7B

Trained with regular LoRA (not quantized/QLoRA) and LoRA rank was 128 and Alpha set to 32. Trained for 1 epoch using A40 for about 23 hours.

Uploaded model

• Developed by: mpasila
• License: apache-2.0
• Finetuned from model : LumiOpen/Viking-7B

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

👁 Image

Base model