Model Card for Alpacazord-Viking-7B

This is a merge of mpasila/Alpacazord-Viking-LoRA-7B.

LoRA trained with text-generation-webui in 4-bit using LumiOpen/Viking-7B as the base model for 1 epoch. Dataset used with the LoRA is mpasila/Alpacazord-V1.

It uses Alpaca format like so:

{
    "instruction,output": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n%instruction%\n\n### Response:\n%output%",
    "instruction,input,output": "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\n%instruction%\n\n### Input:\n%input%\n\n### Response:\n%output%"
}

Merged using this Colab notebook. It might not be the best way to merge a quantized LoRA on to a float16 model but I just wanted to quickly do something. You can try merging it better if you want.

Evaluation

Model	Size	Type	FIN-bench (score)
mpasila/Alpacazord-Viking-7B	7B	Instruct	0.4123
mpasila/Finnish-Alpaca-Small-7B	7B	Instruct	0.3586
mpasila/Finnish-Alpaca-Tiny-V2-7B	7B	Instruct	0.4654
mpasila/Finnish-Viking-Alpaca-V1-7B	7B	Instruct	0.3943
mpasila/NordicAlpaca-Finnish-V1-7B	7B	Instruct	0.3891
Finnish-NLP/llama-7b-finnish-instruct-v0.1	7B	Instruct	0.4365
Finnish-NLP/llama-7b-finnish-instruct-v0.2	7B	Instruct	0.3993
Finnish-NLP/llama-7b-finnish	7B	Base	0.2350
LumiOpen/Viking-7B (1000B)	7B	Base	0.3721
HPLT/gpt-7b-nordic-prerelease	7B	Base	0.3169

Source

FIN-bench scores:

Task	Version	Metric	Value		Stderr
bigbench_analogies	0	multiple_choice_grade	0.5000	±	0.0440
bigbench_arithmetic_1_digit_addition	0	multiple_choice_grade	0.6600	±	0.0476
bigbench_arithmetic_1_digit_division	0	multiple_choice_grade	0.6957	±	0.0981
bigbench_arithmetic_1_digit_multiplication	0	multiple_choice_grade	0.3800	±	0.0488
bigbench_arithmetic_1_digit_subtraction	0	multiple_choice_grade	0.4400	±	0.0499
bigbench_arithmetic_2_digit_addition	0	multiple_choice_grade	0.5000	±	0.0503
bigbench_arithmetic_2_digit_division	0	multiple_choice_grade	0.5400	±	0.0501
bigbench_arithmetic_2_digit_multiplication	0	multiple_choice_grade	0.2100	±	0.0409
bigbench_arithmetic_2_digit_subtraction	0	multiple_choice_grade	0.3100	±	0.0465
bigbench_arithmetic_3_digit_addition	0	multiple_choice_grade	0.5200	±	0.0502
bigbench_arithmetic_3_digit_division	0	multiple_choice_grade	0.2800	±	0.0451
bigbench_arithmetic_3_digit_multiplication	0	multiple_choice_grade	0.1700	±	0.0378
bigbench_arithmetic_3_digit_subtraction	0	multiple_choice_grade	0.5000	±	0.0503
bigbench_arithmetic_4_digit_addition	0	multiple_choice_grade	0.3600	±	0.0482
bigbench_arithmetic_4_digit_division	0	multiple_choice_grade	0.3000	±	0.0461
bigbench_arithmetic_4_digit_multiplication	0	multiple_choice_grade	0.0400	±	0.0197
bigbench_arithmetic_4_digit_subtraction	0	multiple_choice_grade	0.4900	±	0.0502
bigbench_arithmetic_5_digit_addition	0	multiple_choice_grade	0.3700	±	0.0485
bigbench_arithmetic_5_digit_division	0	multiple_choice_grade	0.1400	±	0.0349
bigbench_arithmetic_5_digit_multiplication	0	multiple_choice_grade	0.0000	±	0.0000
bigbench_arithmetic_5_digit_subtraction	0	multiple_choice_grade	0.4500	±	0.0500
bigbench_cause_and_effect_one_sentence	0	multiple_choice_grade	0.5882	±	0.0696
bigbench_cause_and_effect_one_sentence_no_prompt	0	multiple_choice_grade	0.7451	±	0.0616
bigbench_cause_and_effect_two_sentences	0	multiple_choice_grade	0.4706	±	0.0706
bigbench_emotions	0	multiple_choice_grade	0.2938	±	0.0361
bigbench_empirical_judgments	0	multiple_choice_grade	0.3333	±	0.0476
bigbench_general_knowledge	0	multiple_choice_grade	0.3429	±	0.0571
bigbench_hhh_alignment_harmless	0	multiple_choice_grade	0.3621	±	0.0637
bigbench_hhh_alignment_helpful	0	multiple_choice_grade	0.3559	±	0.0629
bigbench_hhh_alignment_honest	0	multiple_choice_grade	0.4068	±	0.0645
bigbench_hhh_alignment_other	0	multiple_choice_grade	0.5581	±	0.0766
bigbench_intent_recognition	0	multiple_choice_grade	0.2587	±	0.0167
bigbench_misconceptions	0	multiple_choice_grade	0.5299	±	0.0433
bigbench_paraphrase	0	multiple_choice_grade	0.5050	±	0.0354
bigbench_sentence_ambiguity	0	multiple_choice_grade	0.5000	±	0.0651
bigbench_similarities_abstraction	0	multiple_choice_grade	0.7368	±	0.0508

Framework versions

• PEFT 0.8.2