---
license: apache-2.0
tags:
- moe
- merge
- epfl-llm/meditron-7b
- medalpaca/medalpaca-7b
- chaoyi-wu/PMC_LLAMA_7B_10_epoch
- microsoft/Orca-2-7b
model-index:
- name: Medorca-4x7b
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 29.35
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/Medorca-4x7b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 25.72
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/Medorca-4x7b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 24.28
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/Medorca-4x7b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 48.42
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/Medorca-4x7b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 48.3
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/Medorca-4x7b
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 0.0
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Technoculture/Medorca-4x7b
      name: Open LLM Leaderboard
---

# Medorca-4x7b

Mediquad-orca-20B is a Mixure of Experts (MoE) made with the following models:
* [epfl-llm/meditron-7b](https://huggingface.co/epfl-llm/meditron-7b)
* [medalpaca/medalpaca-7b](https://huggingface.co/medalpaca/medalpaca-7b)
* [chaoyi-wu/PMC_LLAMA_7B_10_epoch](https://huggingface.co/chaoyi-wu/PMC_LLAMA_7B_10_epoch)
* [microsoft/Orca-2-7b](https://huggingface.co/microsoft/Orca-2-7b)

## Evaluations

[open_llm_leaderboard](https://huggingface.co/datasets/open-llm-leaderboard/details_Technoculture__Mediquad-orca-20B)

| Benchmark | Medorca-4x7b | Orca-2-7b | meditron-7b | meditron-70b |
| --- | --- | --- | --- | --- |
| MedMCQA |  |  |  |  |
| ClosedPubMedQA |  |  |  |  |
| PubMedQA |  |  |  |  |
| MedQA |  |  |  |  |
| MedQA4 |  |  |  |  |
| MedicationQA |  |  |  |  |
| MMLU Medical |  |  |  |  |
| MMLU | 24.28 | 56.37 |  |  |
| TruthfulQA | 48.42 | 52.45 |  |  |
| GSM8K | 0 | 47.2 |  |  |
| ARC | 29.35 | 54.1 |  |  |
| HellaSwag | 25.72 | 76.19 |  |  |
| Winogrande | 48.3 | 73.48 |  |  |

## 🧩 Configuration

```yamlbase_model: microsoft/Orca-2-7b
gate_mode: hidden
dtype: bfloat16
experts:
  - source_model: epfl-llm/meditron-7b
    positive_prompts:
      - "How does sleep affect cardiovascular health?"
      - "When discussing diabetes management, the key factors to consider are"
      - "The differential diagnosis for a headache with visual aura could include"
    negative_prompts:
      - "What are the environmental impacts of deforestation?"
      - "The recent advancements in artificial intelligence have led to developments in"
  - source_model: medalpaca/medalpaca-7b
    positive_prompts:
      - "When discussing diabetes management, the key factors to consider are"
      - "The differential diagnosis for a headache with visual aura could include"
    negative_prompts:
      - "Recommend a good recipe for a vegetarian lasagna."
      - "The fundamental concepts in economics include ideas like supply and demand, which explain"
  - source_model: chaoyi-wu/PMC_LLAMA_7B_10_epoch
    positive_prompts:
      - "How does sleep affect cardiovascular health?"
      - "When discussing diabetes management, the key factors to consider are"
    negative_prompts:
      - "Recommend a good recipe for a vegetarian lasagna."
      - "The recent advancements in artificial intelligence have led to developments in"
      - "The fundamental concepts in economics include ideas like supply and demand, which explain"
  - source_model: microsoft/Orca-2-7b
    positive_prompts:
      - "Here is a funny joke for you -"
      - "When considering the ethical implications of artificial intelligence, one must take into account"
      - "In strategic planning, a company must analyze its strengths and weaknesses, which involves"
      - "Understanding consumer behavior in marketing requires considering factors like"
      - "The debate on climate change solutions hinges on arguments that"
    negative_prompts:
      - "In discussing dietary adjustments for managing hypertension, it's crucial to emphasize"
      - "For early detection of melanoma, dermatologists recommend that patients regularly check their skin for"
      - "Explaining the importance of vaccination, a healthcare professional should highlight"

```

## 💻 Usage

```python
!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Technoculture/Mediquad-orca-20B"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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"])
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Technoculture__Medorca-4x7b)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |29.35|
|AI2 Reasoning Challenge (25-Shot)|29.35|
|HellaSwag (10-Shot)              |25.72|
|MMLU (5-Shot)                    |24.28|
|TruthfulQA (0-shot)              |48.42|
|Winogrande (5-shot)              |48.30|
|GSM8k (5-shot)                   | 0.00|