---
language:
- fi
library_name: peft
base_model: mpasila/gpt3-finnish-8B-gptq-4bit
license: apache-2.0
datasets:
- Finnish-NLP/Capybara-fi-deepl-translated-sft
- mpasila/Capybara-fi-deepl-translated-sft-alpaca
---

# Model Card for Capybara-Finnish-V1-8B-LoRA

LoRA trained using [mpasila/gpt3-finnish-8B-gptq-4bit](https://huggingface.co/mpasila/gpt3-finnish-8B-gptq-4bit/) as the base model. Also the quantized model is based on this [TurkuNLP/gpt3-finnish-8B](https://huggingface.co/TurkuNLP/gpt3-finnish-8B/). Dataset used with the LoRA is [Finnish-NLP/Capybara-fi-deepl-translated-sft](https://huggingface.co/datasets/Finnish-NLP/Capybara-fi-deepl-translated-sft/) with some modifications so it uses Alpaca formatting [modified dataset](https://huggingface.co/datasets/mpasila/Capybara-fi-deepl-translated-sft-alpaca/).

It uses Alpaca format but with a translated instruction at the start:
```
{
    "instruction,output": "Alla on ohje, jossa kuvataan tehtävä. Kirjoita vastaus, joka täyttää pyynnön asianmukaisesti.\n\n### Instruction:\n%instruction%\n\n### Response:\n%output%",
    "instruction,input,output": "Alla on ohje, jossa kuvataan tehtävä ja joka on yhdistetty kontekstia lisäävään syötteeseen. Kirjoita vastaus, joka täyttää pyynnön asianmukaisesti.\n\n### Instruction:\n%instruction%\n\n### Input:\n%input%\n\n### Response:\n%output%"
}

```

Using the following settings:
```json
{
  "lora_name": "Capybara_Finnish_V1",
  "always_override": false,
  "q_proj_en": true,
  "v_proj_en": true,
  "k_proj_en": false,
  "o_proj_en": false,
  "gate_proj_en": false,
  "down_proj_en": false,
  "up_proj_en": false,
  "save_steps": 250.0,
  "micro_batch_size": 4,
  "batch_size": 128,
  "epochs": 3.0,
  "learning_rate": "3e-4",
  "lr_scheduler_type": "linear",
  "lora_rank": 32,
  "lora_alpha": 64,
  "lora_dropout": 0.05,
  "cutoff_len": 256,
  "dataset": "capybara_finnish_v1.1",
  "eval_dataset": "None",
  "format": "alpaca-format-finnish",
  "eval_steps": 100.0,
  "raw_text_file": "None",
  "overlap_len": 128,
  "newline_favor_len": 128,
  "higher_rank_limit": false,
  "warmup_steps": 100.0,
  "optimizer": "adamw_torch",
  "hard_cut_string": "\\n\\n\\n",
  "train_only_after": "",
  "stop_at_loss": 0,
  "add_eos_token": false,
  "min_chars": 0.0,
  "report_to": "None"
}
```

### Framework versions

- PEFT 0.8.2