Mistral-Instruct-Ukrainian-SFT/README.md

---
license: apache-2.0
library_name: transformers
model-index:
- name: Mistral-Instruct-Ukrainian-SFT
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 57.85
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Radu1999/Mistral-Instruct-Ukrainian-SFT
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 83.12
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Radu1999/Mistral-Instruct-Ukrainian-SFT
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 60.95
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Radu1999/Mistral-Instruct-Ukrainian-SFT
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 54.14
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Radu1999/Mistral-Instruct-Ukrainian-SFT
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 77.51
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Radu1999/Mistral-Instruct-Ukrainian-SFT
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 39.42
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Radu1999/Mistral-Instruct-Ukrainian-SFT
      name: Open LLM Leaderboard
---

# Model card for Mistral-Instruct-Ukrainian-SFT

Supervised finetuning of Mistral-7B-Instruct-v0.2 on Ukrainian datasets.


## Instruction format

In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens.

E.g.
```
text = "[INST]Відповідайте лише буквою правильної відповіді: Елементи експресіонізму наявні у творі: A. «Камінний хрест», B. «Інститутка», C. «Маруся», D. «Людина»[/INST]"
```

This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:

## Model Architecture
This instruction model is based on Mistral-7B-v0.2, a transformer model with the following architecture choices:
- Grouped-Query Attention
- Sliding-Window Attention
- Byte-fallback BPE tokenizer

## Datasets
- [UA-SQUAD](https://huggingface.co/datasets/FIdo-AI/ua-squad/resolve/main/ua_squad_dataset.json)
- [Ukrainian StackExchange](https://huggingface.co/datasets/zeusfsx/ukrainian-stackexchange)
- [UAlpaca Dataset](https://github.com/robinhad/kruk/blob/main/data/cc-by-nc/alpaca_data_translated.json)
- [Ukrainian Subset from Belebele Dataset](https://github.com/facebookresearch/belebele)
- [Ukrainian Subset from XQA](https://github.com/thunlp/XQA)
  
## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Radu1999/Mistral-Instruct-Ukrainian-SFT"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```

## Author

Radu Chivereanu
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Radu1999__Mistral-Instruct-Ukrainian-SFT)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |62.17|
|AI2 Reasoning Challenge (25-Shot)|57.85|
|HellaSwag (10-Shot)              |83.12|
|MMLU (5-Shot)                    |60.95|
|TruthfulQA (0-shot)              |54.14|
|Winogrande (5-shot)              |77.51|
|GSM8k (5-shot)                   |39.42|