README.md

---
language:
- fi
base_model: LumiOpen/Viking-7B
license: apache-2.0
datasets:
- mpasila/Alpacazord-V1
---
This is an ExLlamaV2 quantized model in 4bpw of [mpasila/Alpacazord-Viking-7B](https://huggingface.co/mpasila/Alpacazord-Viking-7B) using the default calibration dataset.

# Original Model card:

# Model Card for Alpacazord-Viking-7B

This is a merge of [mpasila/Alpacazord-Viking-LoRA-7B](https://huggingface.co/mpasila/Alpacazord-Viking-LoRA-7B/).

LoRA trained with text-generation-webui in 4-bit using [LumiOpen/Viking-7B](https://huggingface.co/LumiOpen/Viking-7B/) as the base model for 1 epoch. Dataset used with the LoRA is [mpasila/Alpacazord-V1](https://huggingface.co/datasets/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](https://colab.research.google.com/drive/1a76Y21GfPtmVs71Uztlgk2xzPA4_vVjs?usp=sharing). 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 | |
| [mpasila/Finnish-Viking-Alpaca-V1-7B](https://huggingface.co/mpasila/Finnish-Viking-Alpaca-V1-7B) | 7B | Instruct | 0.3943 |
| [mpasila/NordicAlpaca-Finnish-V1-7B](https://huggingface.co/mpasila/NordicAlpaca-Finnish-V1-7B) | 7B | Instruct | 0.3891 |
| [Finnish-NLP/llama-7b-finnish-instruct-v0.1](https://huggingface.co/Finnish-NLP/llama-7b-finnish-instruct-v0.1) | 7B | Instruct | **0.4365** |
| [Finnish-NLP/llama-7b-finnish-instruct-v0.2](https://huggingface.co/Finnish-NLP/llama-7b-finnish-instruct-v0.2) | 7B | Instruct | 0.3993 |
| [Finnish-NLP/llama-7b-finnish](https://huggingface.co/Finnish-NLP/llama-7b-finnish) | 7B | Base | 0.2350 |
| [LumiOpen/Viking-7B (1000B)](https://huggingface.co/LumiOpen/Viking-7B) | 7B | Base | 0.3721 |
| [HPLT/gpt-7b-nordic-prerelease](https://huggingface.co/HPLT/gpt-7b-nordic-prerelease) | 7B | Base | 0.3169 |

[Source](https://docs.google.com/spreadsheets/d/1rqJb9dQVihg-Z1_Ras1L_-wuzPg9xNzpdmM2x5HueeY/edit?usp=sharing)

#### FIN-bench scores:

Will add later. And possibly other evals?????

### Framework versions

- PEFT 0.8.2