---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- maywell/PiVoT-0.1-Starling-LM-RP
- WizardLM/WizardMath-7B-V1.1
base_model:
- maywell/PiVoT-0.1-Starling-LM-RP
- WizardLM/WizardMath-7B-V1.1
model-index:
- name: Rose-2x7B
  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: 65.27
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uproai/Rose-2x7B
      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: 85.7
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uproai/Rose-2x7B
      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: 64.37
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uproai/Rose-2x7B
      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: 49.32
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uproai/Rose-2x7B
      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: 79.79
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uproai/Rose-2x7B
      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: 69.14
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uproai/Rose-2x7B
      name: Open LLM Leaderboard
---

# Rose-2x7B

Rose-2x7B is a Mixure of Experts (MoE) made with the following models using [Mergekit](https://github.com/cg123/mergekit):
* [maywell/PiVoT-0.1-Starling-LM-RP](https://huggingface.co/maywell/PiVoT-0.1-Starling-LM-RP)
* [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)

```bash
mergekit-moe mergekit_moe.yaml merge --copy-tokenizer --device cuda --low-cpu-memory
```

## 🧩 Configuration

```yaml
base_model: uproai/ros-7b-v1
experts:
  - source_model: maywell/PiVoT-0.1-Starling-LM-RP
    positive_prompts:
    - "storywriting"
    - "write"
    - "scene"
    - "story"
    - "character"
  - source_model: WizardLM/WizardMath-7B-V1.1
    positive_prompts:
    - "reason"
    - "math"
    - "mathematics"
    - "solve"
    - "count"
tokenizer_source: union
```

## 💻 Usage

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

from transformers import AutoTokenizer
import transformers
import torch

model = "uproai/Rose-2x7B"

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_uproai__Rose-2x7B)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |68.93|
|AI2 Reasoning Challenge (25-Shot)|65.27|
|HellaSwag (10-Shot)              |85.70|
|MMLU (5-Shot)                    |64.37|
|TruthfulQA (0-shot)              |49.32|
|Winogrande (5-shot)              |79.79|
|GSM8k (5-shot)                   |69.14|