Update README.md

README.md

@@ -1,3 +1,132 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+datasets:
+- IMISLab/CulturaQA
+language:
+- el
+metrics:
+- accuracy
+- bertscore
+base_model:
+- mistralai/Ministral-3-8B-Instruct-2512-BF16
+pipeline_tag: text-generation
+tags:
+- greek
+- nlp
+- genai
+- LLM
+- QA
+- chat
+- maistros
+---
+# Maistros-8B-Instruct: A Greek Large Language Model adapted through Knowledge Distillation from Large Reasoning Models
+
+We introduce Maistros-8B-Instruct, a Greek-adapted LLM based on `mistralai/Ministral-3-8B-Instruct-2512-BF16` fine-tuned using Low-Rank Adaptation (LoRA) on [CulturaQA](https://huggingface.co/datasets/IMISLab/CulturaQA).   
+For information regarding the model training, validation and evaluation, as well as its limitations see the [arxiv preprint](). 
+
+<div align="center">
+  <img src="Maistros-Greek.png" width="50%" alt="Maistros Greek logo"/>
+</div>
+
+## Model Information
+
+- 256k context length (approx. 150,000 Greek words).
+- We extend the training of `Ministral-3-8B-Instruct-2512-BF16` with Greek linguistic and cultural knowledge from the training part of [CulturaQA](https://huggingface.co/datasets/IMISLab/CulturaQA).
+- We use LoRA fine-tuning to mitigate catastrophic forgetting and retain the base models' capabilities.
+- We merge the adapted weights from LoRA fine-tuning to the base model to produce Maistros-8B-Instruct, a specialized Greek LLM.
+- Maistros-8B-Instruct achieves state-of-the-art performance in most Greek QA datasets, when compared to other open-weight models.
+
+## Evaluation
+
+| Acc (%) | DemosQA | GPCR | INCLUDE | Greek ASEP MCQA | Greek Medical MCQA | Plutus QA | Greek Truthful QA | Greek MMLU (Greek-specific) | CulturaQA |
+| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| **Open-Weights Models** | | | | | | | | | |
+| **Maistros 8B (Ours)** | 50.83 | **64.42** | **58.70** | **67.25** | **49.54** | **73.33** | 53.37 | **78.17** | **71.99** |
+| Ministral 3 8B | **51.67** | 59.62 | 54.17 | 63.25 | 47.92 | 65.33 | 52.51 | 76.23 | 71.03 |
+| Krikri 8B | 49.50 | 54.81 | 50.54 | 63.08 | 45.37 | 64.44 | **54.83** | 71.04 | 71.31 |
+| Plutus 8B | 45.67 | 50.00 | 48.37 | 62.92 | 39.35 | 57.33 | 34.52 | 70.38 | 67.44 |
+| EuroLLM v2 9B | 41.50 | 53.85 | 39.13 | 46.08 | 31.71 | 42.67 | 36.72 | 58.17 | 70.33 |
+| Gemma 3n E4B | 47.17 | 60.10 | 50.00 | 57.75 | 43.75 | 53.78 | 46.76 | 71.39 | 69.10 |
+| Qwen 3 8B | 48.83 | 31.73 | 49.28 | 54.58 | 36.64 | 63.56 | 42.72 | 67.57 | 68.73 |
+| **Proprietary Models** | | | | | | | | | |
+| Gemini 3 flash | **55.67** | **88.46** | **88.77** | **94.75** | **92.82** | **89.78** | **88.62** | **95.03** | 73.97 |
+| GPT-5 mini | 53.00 | 77.40 | 74.46 | 78.92 | 78.01 | 76.89 | 75.89 | 87.49 | **75.09** |
+
+## How to load and run the model.
+Use the following code to run the model locally or you can host the model using [vLLM]('https://vllm.ai/').
+
+```python
+from transformers import (
+    AutoTokenizer,
+    Mistral3ForConditionalGeneration, 
+    set_seed
+)
+
+# Set the model path, device and a random seed for reproducibility.
+model_path = 'IMISLab/Maistros-8B-Instruct'
+device = 'cuda'
+set_seed(42)
+
+# Loading the model tokenizer.
+self.tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code = True)
+
+# Causal Language Models predict tokens from left to right and use EOS token for padding.
+tokenizer.pad_token = tokenizer.eos_token
+tokenizer.padding_side = 'right'
+
+
+# Load the model from the path to the device and set it in evaluation mode.
+self.model = Mistral3ForConditionalGeneration.from_pretrained(model_path, device_map = self.device, trust_remote_code = True)
+self.model.eval()
+
+# Set the system, instruction and user prompts.
+system_prompt = ''
+instruction_prompt = ''
+user_prompt = ''
+
+# Defining the message template.
+messages = [
+    {'role': 'system', 'content': [{'type': 'text', 'text': system_prompt}]}
+    {'role': 'user', 'content': [{'type': 'text', 'text': '\n\n'.join((instruction_prompt, user_prompt))}]}
+]
+
+# Applying the tokenizer chat template.
+tokenized = self.tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt = True,  
+    return_tensors = 'pt', 
+    return_dict = True
+)
+
+# Sending the tokenized instances to the device.  
+tokenized = {k: v.to(self.device) for k, v in tokenized.items()}
+input_len = len(tokenized['input_ids'][0])
+
+# Generating the model output.
+output = self.model.generate(
+    **tokenized,
+    max_new_tokens = self.max_output_tokens,
+    do_sample = False, # Equivalent to temperature = 0.0
+    temperature = None,
+    top_p = None,
+    top_k = None
+)
+
+# Decoding the assistant part of the output and printing it.
+decoded_output = self.tokenizer.decode(output[0][input_len:], skip_special_tokens = True)
+print(decoded_output)
+```
+
+## Contact
+
+If you have any questions/feedback about the dataset please e-mail one of the following authors:
+```
+giarelis@ceid.upatras.gr
+cmastrokostas@ac.upatras.gr
+karacap@upatras.gr
+```
+## Citation
+
+```
+TBA
+```