README.md

metadata

language:
  - fi
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
base_model: LumiOpen/Viking-7B
datasets:
  - mpasila/Finnish-ShareGPT-Tiny-V1-1
library_name: peft

Trained for 2 epochs using mpasila/Finnish-ShareGPT-Tiny-V1-1 in 2048 context with LoRA Rank set to 256 with Alpha set to 512.

Prompt format: ChatML

Works better with a system prompt.

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.