metadata
base_model: utter-project/EuroLLM-9B
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
- fi
- 'no'
- nb
- da
- sv
- is
datasets:
- mpasila/Viking-Instruct-Mix
- saillab/alpaca-icelandic-cleaned
- kobprof/skolegpt-instruct
- tollefj/nor-instruct-cleaned
- skvarre/sv-instruct-v1
- Gryphe/Sonnet3.5-SlimOrcaDedupCleaned-20k
- LumiOpen/instruction-collection-fin
- neph1/Alpaca-Lora-GPT4-Swedish-Refined
Uses same data as mpasila/Viking-SlimInstruct-V1-7B.
Uses ChatML as usual.
LoRA: mpasila/EuroLLM-Nordic-Instruct-LoRA-9B
Uses the following datasets:
saillab/alpaca-icelandic-cleaned, kobprof/skolegpt-instruct, tollefj/nor-instruct-cleaned, skvarre/sv-instruct-v1, Gryphe/Sonnet3.5-SlimOrcaDedupCleaned-20k, LumiOpen/instruction-collection-fin, neph1/Alpaca-Lora-GPT4-Swedish-Refined
Uploaded EuroLLM-Nordic-Instruct-9B model
- Developed by: mpasila
- License: apache-2.0
- Finetuned from model : utter-project/EuroLLM-9B
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
