---
language:
- fi
library_name: peft
base_model: HPLT/gpt-7b-nordic-prerelease
license: apache-2.0
datasets:
- pinzhenchen/alpaca-cleaned-fi
---

# Model Card for Alpaca-Finnish-V1-7B-LoRA

LoRA trained in 4-bit using [HPLT/gpt-7b-nordic-prerelease](https://huggingface.co/HPLT/gpt-7b-nordic-prerelease/) as the base model for 1 epoch. Dataset used with the LoRA is [pinzhenchen/alpaca-cleaned-fi](https://huggingface.co/datasets/pinzhenchen/alpaca-cleaned-fi/).

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": "Alpaca-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": 256,
  "lora_alpha": 512,
  "lora_dropout": 0.05,
  "cutoff_len": 384,
  "dataset": "alpaca_data_cleaned.fi",
  "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