license, library_name, model-index

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

💻 Usage

!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

Detailed results can be found here

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