README.md

---
language:
- en
license: llama3.2
library_name: transformers
base_model:
- meta-llama/Llama-3.2-1B-Instruct
- Llama-3.2-SUN-2.5B-chat
datasets:
- argilla/OpenHermesPreferences
- argilla/magpie-ultra-v0.1
- argilla/Capybara-Preferences-Filtered
- mlabonne/open-perfectblend
- HuggingFaceTB/everyday-conversations-llama3.1-2k
- WizardLMTeam/WizardLM_evol_instruct_V2_196k
- ProlificAI/social-reasoning-rlhf
- allenai/tulu-3-sft-mixture
- allenai/llama-3.1-tulu-3-8b-preference-mixture
pipeline_tag: text-generation
model-index:
- name: Llama-3.2-SUN-1B-Instruct
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: HuggingFaceH4/ifeval
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 64.13
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-1B-Instruct
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: BBH
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 9.18
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-1B-Instruct
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: hendrycks/competition_math
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 4.61
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-1B-Instruct
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 0.0
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-1B-Instruct
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 4.05
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-1B-Instruct
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 8.68
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-1B-Instruct
      name: Open LLM Leaderboard
---

# MedIT SUN 1B Instruct

<div align="center">
  <img src="https://i.ibb.co/PF0TdMJ/imagine-image-9a56cee7-0f4f-4cc2-b265-a5b8d04f266b.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>

**Base Model**
- Llama 3.2 1B -> MedIT SUN 2.5B -> MedIT SUN 1B -> Knowledge Injection from Llama 3.1 8B Instruct

**Mesh Size**
- 1B to 2.5B parameters [MedIT SUN 2.5B](https://huggingface.co/meditsolutions/Llama-3.2-SUN-2.5B-chat) -> layers mesh using MedIT-mesh technique and downscaled to 1B

**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: instruct-1.0.0

**Key Features**
- Built on Llama 3.2 architecture
- Upscaled from 1B to 2.47B parameters
- Optimized for open-ended conversations
- Incorporates supervised fine-tuning for improved performance
- Layers meshing using the MedIT-mesh technique
- Downscaled to 1B
- Knowledge injection from Llama 3.1 8B Instruct using new technique developed by MedIT Solutions

**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](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_meditsolutions__Llama-3.2-SUN-1B-Instruct)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |15.11|
|IFEval (0-Shot)    |64.13|
|BBH (3-Shot)       | 9.18|
|MATH Lvl 5 (4-Shot)| 4.61|
|GPQA (0-shot)      | 0.00|
|MuSR (0-shot)      | 4.05|
|MMLU-PRO (5-shot)  | 8.68|