MedIT SUN
Collection
Llama 3.2 1B upscaled to 2.5B parameters
•
3 items
•
Updated
•
1
MedIT SUN 2.5B
Base Model
- Llama 3.2 1B
Extended Size
- 1B to 2.5B parameters
Extension Method
- Proprietary technique developed by MedIT Solutions
Fine-tuning
- Open (or open subsets allowing for commercial use) open datasets from HF
- Open (or open subsets allowing for commercial use) SFT datasets from HF
Training Status
- Current version: chat-1.0.0
Key Features
- Built on Llama 3.2 architecture
- Expanded from 1B to 2.47B parameters
- Optimized for open-ended conversations
- Incorporates supervised fine-tuning for improved performance
Use Case
- General conversation and task-oriented interactions
Limitations As the model is still in training, performance and capabilities may vary. Users should be aware that the model is not in its final form and may exhibit inconsistencies or limitations typical of in-progress AI models.
Disclaimer and Safety Considerations The Model is designed to be used as a smart assistant but not as a knowledge source within your applications, systems, or environments. It is not intended to provide 100% accurate answers, especially in scenarios where high precision and accuracy are
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 13.65 |
| IFEval (0-Shot) | 56.04 |
| BBH (3-Shot) | 9.41 |
| MATH Lvl 5 (4-Shot) | 5.06 |
| GPQA (0-shot) | 1.23 |
| MuSR (0-shot) | 1.11 |
| MMLU-PRO (5-shot) | 9.04 |
- Downloads last month
- 685
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for meditsolutions/Llama-3.2-SUN-2.5B-chat
Datasets used to train meditsolutions/Llama-3.2-SUN-2.5B-chat
Space using meditsolutions/Llama-3.2-SUN-2.5B-chat 1
Collection including meditsolutions/Llama-3.2-SUN-2.5B-chat
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard56.040
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard9.410
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard5.060
- acc_norm on GPQA (0-shot)Open LLM Leaderboard1.230
- acc_norm on MuSR (0-shot)Open LLM Leaderboard1.110
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard9.040