65 lines
3.2 KiB
Markdown
65 lines
3.2 KiB
Markdown
---
|
|
license: apache-2.0
|
|
base_model:
|
|
- speakleash/Bielik-11B-v2.3-Instruct
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- medit-merge
|
|
language:
|
|
- pl
|
|
- en
|
|
---
|
|
|
|
<div align="center">
|
|
<img src="https://i.ibb.co/YLfCzXR/imagine-image-c680e106-e404-45e5-98da-af700ffe41f4.png" alt="Llama-3.2-MedIT-SUN-2.5B" style="border-radius: 10px; box-shadow: 0 4px 8px 0 rgba(0, 0, 0, 0.2), 0 6px 20px 0 rgba(0, 0, 0, 0.19); max-width: 100%; height: auto;">
|
|
</div>
|
|
|
|
# Marsh Harrier
|
|
|
|
The Marsh Harrier (MSH) is a language model developed by MedIT Solutions using an advanced checkpoint merging technique. It represents a novel fusion of the Speakleash Bielik 11B v2.3 Instruct and Speakleash Bielik 11B v2 models, employing our proprietary weight-merging methodology.
|
|
|
|
## Key Features:
|
|
- Built on a pioneering approach to neural network weight fusion
|
|
- Supports merging models of identical parameter counts while maintaining architecture flexibility
|
|
- Demonstrates superior performance compared to its base models
|
|
- Optimized for Polish language understanding and generation
|
|
|
|
## Performance:
|
|
The model shows significant improvements over its predecessors across multiple metrics in the Open PL LLM Leaderboard evaluation framework (0-shot), which is part of the SpeakLeash.org open-science initiative.
|
|
|
|
Technical Details:
|
|
- Base Models: [Speakleash Bielik 11B v2.3 Instruct](https://huggingface.co/speakleash/Bielik-11B-v2.3-Instruct) and [Bielik 11B v2](https://huggingface.co/speakleash/Bielik-11B-v2)
|
|
- Architecture: Compatible with original Bielik architecture
|
|
- Parameter Count: 11 billion parameters
|
|
- Special Feature: Utilizes MedIT Solutions' proprietary checkpoint merging technology
|
|
|
|
This model represents a step forward in developing the Polish language, demonstrating how merging techniques can enhance model performance while maintaining architectural efficiency.
|
|
|
|
# Polish LLM Open Leaderboard
|
|
|
|
Core Leaderboards:
|
|
- MT-Bench-PL: slight decrease of 0.3 points (8.27 vs 8.56)
|
|
- Open PL LLM Leaderboard: improved performance by 0.09 points (65.80 vs 65.71)
|
|
|
|
Sentiment Analysis (PolEmo2):
|
|
- In-domain accuracy: Matches Bielik at 77.70%
|
|
- Out-of-domain accuracy: Improved performance at 79.76% (vs 79.35%)
|
|
|
|
Text Classification Tasks:
|
|
- 8tags classification: Significant improvement of ~3pp (76.14% vs 73.17%)
|
|
- Belebele benchmark: Matching performance at 88.56%
|
|
- CBD task: Substantial F1 score improvement by 10pp (23.91% vs 13.73%)
|
|
|
|
Language Understanding:
|
|
- DYK ("Did you know..."): Improved F1 score (69.77% vs 69.14%)
|
|
- Named Entity Recognition (KLEJ NER): Notable improvement of ~8pp (45.53% vs 37.61%)
|
|
- PolQA reranking: Slight decrease (81.99% vs 83.21%)
|
|
- PPC: Enhanced accuracy (78.00% vs 77.20%)
|
|
- PSC: Minor F1 score decrease (90.46% vs 93.63%)
|
|
|
|
Overall Performance:
|
|
MSH-v1 achieves a higher average score of 71.18% compared to Bielik v2.3's 69.33%, demonstrating the effectiveness of our checkpoint merging technique in improving model performance across diverse NLP tasks.
|
|
|
|
All evaluations were conducted using the Open PL LLM Leaderboard framework (0-shot) as part of the SpeakLeash.org open-science initiative.
|
|
|
|
Kudos to the **[SpeakLeash](https://speakleash.org)** project and **[ACK Cyfronet AGH](https://www.cyfronet.pl/)** for their extraordinary work. |